import numpy as np
import matplotlib.pyplot as plt
from matplotlib.colors import ListedColormap
from layers import Linear, Sigmoid, Sequential, ReLU
from optim import SGD
from loss import CrossEntropyLoss
import torch
from torch import optim, nn
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
%load_ext autoreload
%autoreload 2
X, y = load_iris(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)
def train_model_torch(X_train, y_train, model, optimizer, criterion, num_epochs=50):
for i in range(num_epochs):
optimizer.zero_grad()
pred = model(X_train)
loss = criterion(pred, y_train)
accuracy = calculate_accuracy_torch(pred, y_train)
loss.backward()
optimizer.step()
print(f'Epoch: {i + 1} | Loss: {loss} | Accuracy: {accuracy}')
def calculate_accuracy_torch(y_pred, y_true):
return torch.sum(torch.argmax(y_pred, axis = 1) == y_true) / y_pred.shape[0]
def train_model(X_train, y_train, model, optimizer, criterion, num_epochs=50):
for i in range(num_epochs):
optimizer.zero_grad()
pred = model(X_train)
loss, loss_grad = criterion(pred, y_train)
accuracy = calculate_accuracy(pred, y_train)
model.backward(loss_grad)
optimizer.step()
print(f'Epoch: {i + 1} | Loss: {loss} | Accuracy: {accuracy}')
def calculate_accuracy(y_pred, y_true):
return np.sum(np.argmax(y_pred, axis = 1) == y_true) / y_pred.shape[0]
model = Sequential(
Linear(4, 3),
)
optimizer = SGD(model.parameters(), lr=1e-2)
criterion = CrossEntropyLoss()
train_model(X_train, y_train, model, optimizer, criterion, 5000)
Loss: 0.20193335540629617 | Accuracy: 0.9714285714285714 Epoch: 4719 | Loss: 0.2019125852638341 | Accuracy: 0.9714285714285714 Epoch: 4720 | Loss: 0.20189182163982958 | Accuracy: 0.9714285714285714 Epoch: 4721 | Loss: 0.20187106453119075 | Accuracy: 0.9714285714285714 Epoch: 4722 | Loss: 0.2018503139348278 | Accuracy: 0.9714285714285714 Epoch: 4723 | Loss: 0.20182956984765246 | Accuracy: 0.9714285714285714 Epoch: 4724 | Loss: 0.2018088322665787 | Accuracy: 0.9714285714285714 Epoch: 4725 | Loss: 0.20178810118852256 | Accuracy: 0.9714285714285714 Epoch: 4726 | Loss: 0.20176737661040148 | Accuracy: 0.9714285714285714 Epoch: 4727 | Loss: 0.20174665852913537 | Accuracy: 0.9714285714285714 Epoch: 4728 | Loss: 0.20172594694164594 | Accuracy: 0.9714285714285714 Epoch: 4729 | Loss: 0.20170524184485655 | Accuracy: 0.9714285714285714 Epoch: 4730 | Loss: 0.2016845432356928 | Accuracy: 0.9714285714285714 Epoch: 4731 | Loss: 0.20166385111108212 | Accuracy: 0.9714285714285714 Epoch: 4732 | Loss: 0.20164316546795383 | Accuracy: 0.9714285714285714 Epoch: 4733 | Loss: 0.20162248630323915 | Accuracy: 0.9714285714285714 Epoch: 4734 | Loss: 0.2016018136138713 | Accuracy: 0.9714285714285714 Epoch: 4735 | Loss: 0.20158114739678537 | Accuracy: 0.9714285714285714 Epoch: 4736 | Loss: 0.20156048764891854 | Accuracy: 0.9714285714285714 Epoch: 4737 | Loss: 0.20153983436720946 | Accuracy: 0.9714285714285714 Epoch: 4738 | Loss: 0.20151918754859918 | Accuracy: 0.9714285714285714 Epoch: 4739 | Loss: 0.20149854719003055 | Accuracy: 0.9714285714285714 Epoch: 4740 | Loss: 0.20147791328844802 | Accuracy: 0.9714285714285714 Epoch: 4741 | Loss: 0.20145728584079836 | Accuracy: 0.9714285714285714 Epoch: 4742 | Loss: 0.20143666484402997 | Accuracy: 0.9714285714285714 Epoch: 4743 | Loss: 0.20141605029509332 | Accuracy: 0.9714285714285714 Epoch: 4744 | Loss: 0.20139544219094077 | Accuracy: 0.9714285714285714 Epoch: 4745 | Loss: 0.20137484052852653 | Accuracy: 0.9714285714285714 Epoch: 4746 | Loss: 0.20135424530480656 | Accuracy: 0.9714285714285714 Epoch: 4747 | Loss: 0.20133365651673907 | Accuracy: 0.9714285714285714 Epoch: 4748 | Loss: 0.20131307416128402 | Accuracy: 0.9714285714285714 Epoch: 4749 | Loss: 0.20129249823540313 | Accuracy: 0.9714285714285714 Epoch: 4750 | Loss: 0.20127192873606006 | Accuracy: 0.9714285714285714 Epoch: 4751 | Loss: 0.20125136566022062 | Accuracy: 0.9714285714285714 Epoch: 4752 | Loss: 0.20123080900485216 | Accuracy: 0.9714285714285714 Epoch: 4753 | Loss: 0.20121025876692425 | Accuracy: 0.9714285714285714 Epoch: 4754 | Loss: 0.20118971494340804 | Accuracy: 0.9714285714285714 Epoch: 4755 | Loss: 0.2011691775312768 | Accuracy: 0.9714285714285714 Epoch: 4756 | Loss: 0.2011486465275057 | Accuracy: 0.9714285714285714 Epoch: 4757 | Loss: 0.20112812192907153 | Accuracy: 0.9714285714285714 Epoch: 4758 | Loss: 0.20110760373295328 | Accuracy: 0.9714285714285714 Epoch: 4759 | Loss: 0.2010870919361316 | Accuracy: 0.9714285714285714 Epoch: 4760 | Loss: 0.20106658653558923 | Accuracy: 0.9714285714285714 Epoch: 4761 | Loss: 0.20104608752831052 | Accuracy: 0.9714285714285714 Epoch: 4762 | Loss: 0.20102559491128202 | Accuracy: 0.9714285714285714 Epoch: 4763 | Loss: 0.2010051086814919 | Accuracy: 0.9714285714285714 Epoch: 4764 | Loss: 0.20098462883593027 | Accuracy: 0.9714285714285714 Epoch: 4765 | Loss: 0.20096415537158924 | Accuracy: 0.9714285714285714 Epoch: 4766 | Loss: 0.2009436882854626 | Accuracy: 0.9714285714285714 Epoch: 4767 | Loss: 0.2009232275745462 | Accuracy: 0.9714285714285714 Epoch: 4768 | Loss: 0.20090277323583766 | Accuracy: 0.9714285714285714 Epoch: 4769 | Loss: 0.20088232526633648 | Accuracy: 0.9714285714285714 Epoch: 4770 | Loss: 0.20086188366304403 | Accuracy: 0.9714285714285714 Epoch: 4771 | Loss: 0.20084144842296353 | Accuracy: 0.9714285714285714 Epoch: 4772 | Loss: 0.20082101954310003 | Accuracy: 0.9714285714285714 Epoch: 4773 | Loss: 0.20080059702046069 | Accuracy: 0.9714285714285714 Epoch: 4774 | Loss: 0.20078018085205418 | Accuracy: 0.9714285714285714 Epoch: 4775 | Loss: 0.20075977103489126 | Accuracy: 0.9714285714285714 Epoch: 4776 | Loss: 0.20073936756598448 | Accuracy: 0.9714285714285714 Epoch: 4777 | Loss: 0.20071897044234815 | Accuracy: 0.9714285714285714 Epoch: 4778 | Loss: 0.20069857966099883 | Accuracy: 0.9714285714285714 Epoch: 4779 | Loss: 0.2006781952189543 | Accuracy: 0.9714285714285714 Epoch: 4780 | Loss: 0.20065781711323474 | Accuracy: 0.9714285714285714 Epoch: 4781 | Loss: 0.200637445340862 | Accuracy: 0.9714285714285714 Epoch: 4782 | Loss: 0.20061707989885966 | Accuracy: 0.9714285714285714 Epoch: 4783 | Loss: 0.20059672078425325 | Accuracy: 0.9714285714285714 Epoch: 4784 | Loss: 0.2005763679940703 | Accuracy: 0.9714285714285714 Epoch: 4785 | Loss: 0.20055602152533988 | Accuracy: 0.9714285714285714 Epoch: 4786 | Loss: 0.20053568137509317 | Accuracy: 0.9714285714285714 Epoch: 4787 | Loss: 0.20051534754036304 | Accuracy: 0.9714285714285714 Epoch: 4788 | Loss: 0.20049502001818428 | Accuracy: 0.9714285714285714 Epoch: 4789 | Loss: 0.2004746988055935 | Accuracy: 0.9714285714285714 Epoch: 4790 | Loss: 0.20045438389962905 | Accuracy: 0.9714285714285714 Epoch: 4791 | Loss: 0.2004340752973314 | Accuracy: 0.9714285714285714 Epoch: 4792 | Loss: 0.20041377299574242 | Accuracy: 0.9714285714285714 Epoch: 4793 | Loss: 0.2003934769919063 | Accuracy: 0.9714285714285714 Epoch: 4794 | Loss: 0.20037318728286874 | Accuracy: 0.9714285714285714 Epoch: 4795 | Loss: 0.20035290386567736 | Accuracy: 0.9714285714285714 Epoch: 4796 | Loss: 0.20033262673738164 | Accuracy: 0.9714285714285714 Epoch: 4797 | Loss: 0.20031235589503277 | Accuracy: 0.9714285714285714 Epoch: 4798 | Loss: 0.20029209133568396 | Accuracy: 0.9714285714285714 Epoch: 4799 | Loss: 0.2002718330563901 | Accuracy: 0.9714285714285714 Epoch: 4800 | Loss: 0.20025158105420804 | Accuracy: 0.9714285714285714 Epoch: 4801 | Loss: 0.2002313353261963 | Accuracy: 0.9714285714285714 Epoch: 4802 | Loss: 0.20021109586941524 | Accuracy: 0.9714285714285714 Epoch: 4803 | Loss: 0.20019086268092723 | Accuracy: 0.9714285714285714 Epoch: 4804 | Loss: 0.2001706357577963 | Accuracy: 0.9714285714285714 Epoch: 4805 | Loss: 0.20015041509708825 | Accuracy: 0.9714285714285714 Epoch: 4806 | Loss: 0.20013020069587084 | Accuracy: 0.9714285714285714 Epoch: 4807 | Loss: 0.20010999255121342 | Accuracy: 0.9714285714285714 Epoch: 4808 | Loss: 0.2000897906601875 | Accuracy: 0.9714285714285714 Epoch: 4809 | Loss: 0.20006959501986618 | Accuracy: 0.9714285714285714 Epoch: 4810 | Loss: 0.20004940562732437 | Accuracy: 0.9714285714285714 Epoch: 4811 | Loss: 0.20002922247963884 | Accuracy: 0.9714285714285714 Epoch: 4812 | Loss: 0.20000904557388816 | Accuracy: 0.9714285714285714 Epoch: 4813 | Loss: 0.1999888749071527 | Accuracy: 0.9714285714285714 Epoch: 4814 | Loss: 0.19996871047651474 | Accuracy: 0.9714285714285714 Epoch: 4815 | Loss: 0.199948552279058 | Accuracy: 0.9714285714285714 Epoch: 4816 | Loss: 0.19992840031186862 | Accuracy: 0.9714285714285714 Epoch: 4817 | Loss: 0.1999082545720339 | Accuracy: 0.9714285714285714 Epoch: 4818 | Loss: 0.19988811505664336 | Accuracy: 0.9714285714285714 Epoch: 4819 | Loss: 0.19986798176278817 | Accuracy: 0.9714285714285714 Epoch: 4820 | Loss: 0.19984785468756144 | Accuracy: 0.9714285714285714 Epoch: 4821 | Loss: 0.19982773382805769 | Accuracy: 0.9714285714285714 Epoch: 4822 | Loss: 0.19980761918137382 | Accuracy: 0.9714285714285714 Epoch: 4823 | Loss: 0.19978751074460796 | Accuracy: 0.9714285714285714 Epoch: 4824 | Loss: 0.19976740851486044 | Accuracy: 0.9714285714285714 Epoch: 4825 | Loss: 0.19974731248923305 | Accuracy: 0.9714285714285714 Epoch: 4826 | Loss: 0.1997272226648297 | Accuracy: 0.9714285714285714 Epoch: 4827 | Loss: 0.1997071390387558 | Accuracy: 0.9714285714285714 Epoch: 4828 | Loss: 0.19968706160811883 | Accuracy: 0.9714285714285714 Epoch: 4829 | Loss: 0.1996669903700278 | Accuracy: 0.9714285714285714 Epoch: 4830 | Loss: 0.19964692532159356 | Accuracy: 0.9714285714285714 Epoch: 4831 | Loss: 0.19962686645992891 | Accuracy: 0.9714285714285714 Epoch: 4832 | Loss: 0.19960681378214826 | Accuracy: 0.9714285714285714 Epoch: 4833 | Loss: 0.19958676728536773 | Accuracy: 0.9714285714285714 Epoch: 4834 | Loss: 0.1995667269667055 | Accuracy: 0.9714285714285714 Epoch: 4835 | Loss: 0.19954669282328139 | Accuracy: 0.9714285714285714 Epoch: 4836 | Loss: 0.19952666485221682 | Accuracy: 0.9714285714285714 Epoch: 4837 | Loss: 0.19950664305063529 | Accuracy: 0.9714285714285714 Epoch: 4838 | Loss: 0.19948662741566173 | Accuracy: 0.9714285714285714 Epoch: 4839 | Loss: 0.1994666179444232 | Accuracy: 0.9714285714285714 Epoch: 4840 | Loss: 0.19944661463404828 | Accuracy: 0.9714285714285714 Epoch: 4841 | Loss: 0.19942661748166748 | Accuracy: 0.9714285714285714 Epoch: 4842 | Loss: 0.19940662648441296 | Accuracy: 0.9714285714285714 Epoch: 4843 | Loss: 0.19938664163941863 | Accuracy: 0.9714285714285714 Epoch: 4844 | Loss: 0.19936666294382033 | Accuracy: 0.9714285714285714 Epoch: 4845 | Loss: 0.19934669039475542 | Accuracy: 0.9714285714285714 Epoch: 4846 | Loss: 0.19932672398936319 | Accuracy: 0.9714285714285714 Epoch: 4847 | Loss: 0.1993067637247849 | Accuracy: 0.9714285714285714 Epoch: 4848 | Loss: 0.19928680959816303 | Accuracy: 0.9714285714285714 Epoch: 4849 | Loss: 0.1992668616066422 | Accuracy: 0.9714285714285714 Epoch: 4850 | Loss: 0.1992469197473688 | Accuracy: 0.9714285714285714 Epoch: 4851 | Loss: 0.1992269840174907 | Accuracy: 0.9714285714285714 Epoch: 4852 | Loss: 0.19920705441415795 | Accuracy: 0.9714285714285714 Epoch: 4853 | Loss: 0.19918713093452198 | Accuracy: 0.9714285714285714 Epoch: 4854 | Loss: 0.19916721357573605 | Accuracy: 0.9714285714285714 Epoch: 4855 | Loss: 0.19914730233495528 | Accuracy: 0.9714285714285714 Epoch: 4856 | Loss: 0.19912739720933656 | Accuracy: 0.9714285714285714 Epoch: 4857 | Loss: 0.19910749819603824 | Accuracy: 0.9714285714285714 Epoch: 4858 | Loss: 0.1990876052922208 | Accuracy: 0.9714285714285714 Epoch: 4859 | Loss: 0.19906771849504626 | Accuracy: 0.9714285714285714 Epoch: 4860 | Loss: 0.19904783780167845 | Accuracy: 0.9714285714285714 Epoch: 4861 | Loss: 0.19902796320928282 | Accuracy: 0.9714285714285714 Epoch: 4862 | Loss: 0.19900809471502667 | Accuracy: 0.9714285714285714 Epoch: 4863 | Loss: 0.198988232316079 | Accuracy: 0.9714285714285714 Epoch: 4864 | Loss: 0.19896837600961056 | Accuracy: 0.9714285714285714 Epoch: 4865 | Loss: 0.19894852579279404 | Accuracy: 0.9714285714285714 Epoch: 4866 | Loss: 0.19892868166280342 | Accuracy: 0.9714285714285714 Epoch: 4867 | Loss: 0.1989088436168148 | Accuracy: 0.9714285714285714 Epoch: 4868 | Loss: 0.19888901165200576 | Accuracy: 0.9714285714285714 Epoch: 4869 | Loss: 0.19886918576555596 | Accuracy: 0.9714285714285714 Epoch: 4870 | Loss: 0.19884936595464633 | Accuracy: 0.9714285714285714 Epoch: 4871 | Loss: 0.1988295522164598 | Accuracy: 0.9714285714285714 Epoch: 4872 | Loss: 0.19880974454818098 | Accuracy: 0.9714285714285714 Epoch: 4873 | Loss: 0.19878994294699637 | Accuracy: 0.9714285714285714 Epoch: 4874 | Loss: 0.1987701474100939 | Accuracy: 0.9714285714285714 Epoch: 4875 | Loss: 0.1987503579346634 | Accuracy: 0.9714285714285714 Epoch: 4876 | Loss: 0.19873057451789636 | Accuracy: 0.9714285714285714 Epoch: 4877 | Loss: 0.1987107971569861 | Accuracy: 0.9714285714285714 Epoch: 4878 | Loss: 0.19869102584912743 | Accuracy: 0.9714285714285714 Epoch: 4879 | Loss: 0.19867126059151727 | Accuracy: 0.9714285714285714 Epoch: 4880 | Loss: 0.1986515013813537 | Accuracy: 0.9714285714285714 Epoch: 4881 | Loss: 0.19863174821583707 | Accuracy: 0.9714285714285714 Epoch: 4882 | Loss: 0.19861200109216912 | Accuracy: 0.9714285714285714 Epoch: 4883 | Loss: 0.19859226000755342 | Accuracy: 0.9714285714285714 Epoch: 4884 | Loss: 0.19857252495919525 | Accuracy: 0.9714285714285714 Epoch: 4885 | Loss: 0.19855279594430142 | Accuracy: 0.9714285714285714 Epoch: 4886 | Loss: 0.19853307296008077 | Accuracy: 0.9714285714285714 Epoch: 4887 | Loss: 0.19851335600374354 | Accuracy: 0.9714285714285714 Epoch: 4888 | Loss: 0.19849364507250197 | Accuracy: 0.9714285714285714 Epoch: 4889 | Loss: 0.19847394016356976 | Accuracy: 0.9714285714285714 Epoch: 4890 | Loss: 0.19845424127416247 | Accuracy: 0.9714285714285714 Epoch: 4891 | Loss: 0.1984345484014973 | Accuracy: 0.9714285714285714 Epoch: 4892 | Loss: 0.198414861542793 | Accuracy: 0.9714285714285714 Epoch: 4893 | Loss: 0.19839518069527035 | Accuracy: 0.9714285714285714 Epoch: 4894 | Loss: 0.19837550585615168 | Accuracy: 0.9714285714285714 Epoch: 4895 | Loss: 0.1983558370226608 | Accuracy: 0.9714285714285714 Epoch: 4896 | Loss: 0.19833617419202354 | Accuracy: 0.9714285714285714 Epoch: 4897 | Loss: 0.19831651736146727 | Accuracy: 0.9714285714285714 Epoch: 4898 | Loss: 0.1982968665282211 | Accuracy: 0.9714285714285714 Epoch: 4899 | Loss: 0.19827722168951578 | Accuracy: 0.9714285714285714 Epoch: 4900 | Loss: 0.1982575828425838 | Accuracy: 0.9714285714285714 Epoch: 4901 | Loss: 0.19823794998465935 | Accuracy: 0.9714285714285714 Epoch: 4902 | Loss: 0.19821832311297818 | Accuracy: 0.9714285714285714 Epoch: 4903 | Loss: 0.19819870222477798 | Accuracy: 0.9714285714285714 Epoch: 4904 | Loss: 0.19817908731729786 | Accuracy: 0.9714285714285714 Epoch: 4905 | Loss: 0.1981594783877788 | Accuracy: 0.9714285714285714 Epoch: 4906 | Loss: 0.1981398754334633 | Accuracy: 0.9714285714285714 Epoch: 4907 | Loss: 0.1981202784515958 | Accuracy: 0.9714285714285714 Epoch: 4908 | Loss: 0.19810068743942216 | Accuracy: 0.9714285714285714 Epoch: 4909 | Loss: 0.19808110239418994 | Accuracy: 0.9714285714285714 Epoch: 4910 | Loss: 0.1980615233131486 | Accuracy: 0.9714285714285714 Epoch: 4911 | Loss: 0.19804195019354898 | Accuracy: 0.9714285714285714 Epoch: 4912 | Loss: 0.19802238303264402 | Accuracy: 0.9714285714285714 Epoch: 4913 | Loss: 0.19800282182768786 | Accuracy: 0.9714285714285714 Epoch: 4914 | Loss: 0.19798326657593657 | Accuracy: 0.9714285714285714 Epoch: 4915 | Loss: 0.1979637172746479 | Accuracy: 0.9714285714285714 Epoch: 4916 | Loss: 0.1979441739210811 | Accuracy: 0.9714285714285714 Epoch: 4917 | Loss: 0.19792463651249728 | Accuracy: 0.9714285714285714 Epoch: 4918 | Loss: 0.19790510504615913 | Accuracy: 0.9714285714285714 Epoch: 4919 | Loss: 0.19788557951933106 | Accuracy: 0.9714285714285714 Epoch: 4920 | Loss: 0.19786605992927908 | Accuracy: 0.9714285714285714 Epoch: 4921 | Loss: 0.1978465462732708 | Accuracy: 0.9714285714285714 Epoch: 4922 | Loss: 0.19782703854857575 | Accuracy: 0.9714285714285714 Epoch: 4923 | Loss: 0.19780753675246493 | Accuracy: 0.9714285714285714 Epoch: 4924 | Loss: 0.19778804088221094 | Accuracy: 0.9714285714285714 Epoch: 4925 | Loss: 0.19776855093508816 | Accuracy: 0.9714285714285714 Epoch: 4926 | Loss: 0.19774906690837268 | Accuracy: 0.9714285714285714 Epoch: 4927 | Loss: 0.19772958879934208 | Accuracy: 0.9714285714285714 Epoch: 4928 | Loss: 0.19771011660527577 | Accuracy: 0.9714285714285714 Epoch: 4929 | Loss: 0.19769065032345462 | Accuracy: 0.9714285714285714 Epoch: 4930 | Loss: 0.1976711899511614 | Accuracy: 0.9714285714285714 Epoch: 4931 | Loss: 0.19765173548568019 | Accuracy: 0.9714285714285714 Epoch: 4932 | Loss: 0.19763228692429713 | Accuracy: 0.9714285714285714 Epoch: 4933 | Loss: 0.1976128442642998 | Accuracy: 0.9714285714285714 Epoch: 4934 | Loss: 0.19759340750297727 | Accuracy: 0.9714285714285714 Epoch: 4935 | Loss: 0.19757397663762047 | Accuracy: 0.9714285714285714 Epoch: 4936 | Loss: 0.1975545516655221 | Accuracy: 0.9714285714285714 Epoch: 4937 | Loss: 0.1975351325839761 | Accuracy: 0.9714285714285714 Epoch: 4938 | Loss: 0.19751571939027843 | Accuracy: 0.9714285714285714 Epoch: 4939 | Loss: 0.19749631208172652 | Accuracy: 0.9714285714285714 Epoch: 4940 | Loss: 0.19747691065561948 | Accuracy: 0.9714285714285714 Epoch: 4941 | Loss: 0.19745751510925802 | Accuracy: 0.9714285714285714 Epoch: 4942 | Loss: 0.19743812543994463 | Accuracy: 0.9714285714285714 Epoch: 4943 | Loss: 0.1974187416449832 | Accuracy: 0.9714285714285714 Epoch: 4944 | Loss: 0.19739936372167935 | Accuracy: 0.9714285714285714 Epoch: 4945 | Loss: 0.19737999166734058 | Accuracy: 0.9714285714285714 Epoch: 4946 | Loss: 0.19736062547927552 | Accuracy: 0.9714285714285714 Epoch: 4947 | Loss: 0.19734126515479503 | Accuracy: 0.9714285714285714 Epoch: 4948 | Loss: 0.19732191069121113 | Accuracy: 0.9714285714285714 Epoch: 4949 | Loss: 0.19730256208583755 | Accuracy: 0.9714285714285714 Epoch: 4950 | Loss: 0.19728321933599005 | Accuracy: 0.9714285714285714 Epoch: 4951 | Loss: 0.1972638824389854 | Accuracy: 0.9714285714285714 Epoch: 4952 | Loss: 0.19724455139214234 | Accuracy: 0.9714285714285714 Epoch: 4953 | Loss: 0.19722522619278138 | Accuracy: 0.9714285714285714 Epoch: 4954 | Loss: 0.1972059068382244 | Accuracy: 0.9714285714285714 Epoch: 4955 | Loss: 0.19718659332579477 | Accuracy: 0.9714285714285714 Epoch: 4956 | Loss: 0.197167285652818 | Accuracy: 0.9714285714285714 Epoch: 4957 | Loss: 0.1971479838166206 | Accuracy: 0.9714285714285714 Epoch: 4958 | Loss: 0.1971286878145313 | Accuracy: 0.9714285714285714 Epoch: 4959 | Loss: 0.19710939764388 | Accuracy: 0.9714285714285714 Epoch: 4960 | Loss: 0.19709011330199835 | Accuracy: 0.9714285714285714 Epoch: 4961 | Loss: 0.19707083478621962 | Accuracy: 0.9714285714285714 Epoch: 4962 | Loss: 0.1970515620938789 | Accuracy: 0.9714285714285714 Epoch: 4963 | Loss: 0.19703229522231241 | Accuracy: 0.9714285714285714 Epoch: 4964 | Loss: 0.19701303416885857 | Accuracy: 0.9714285714285714 Epoch: 4965 | Loss: 0.19699377893085687 | Accuracy: 0.9714285714285714 Epoch: 4966 | Loss: 0.19697452950564884 | Accuracy: 0.9714285714285714 Epoch: 4967 | Loss: 0.1969552858905773 | Accuracy: 0.9714285714285714 Epoch: 4968 | Loss: 0.19693604808298698 | Accuracy: 0.9714285714285714 Epoch: 4969 | Loss: 0.19691681608022385 | Accuracy: 0.9714285714285714 Epoch: 4970 | Loss: 0.19689758987963576 | Accuracy: 0.9714285714285714 Epoch: 4971 | Loss: 0.1968783694785722 | Accuracy: 0.9714285714285714 Epoch: 4972 | Loss: 0.19685915487438393 | Accuracy: 0.9714285714285714 Epoch: 4973 | Loss: 0.19683994606442368 | Accuracy: 0.9714285714285714 Epoch: 4974 | Loss: 0.19682074304604563 | Accuracy: 0.9714285714285714 Epoch: 4975 | Loss: 0.1968015458166055 | Accuracy: 0.9714285714285714 Epoch: 4976 | Loss: 0.19678235437346073 | Accuracy: 0.9714285714285714 Epoch: 4977 | Loss: 0.19676316871397015 | Accuracy: 0.9714285714285714 Epoch: 4978 | Loss: 0.19674398883549452 | Accuracy: 0.9714285714285714 Epoch: 4979 | Loss: 0.19672481473539583 | Accuracy: 0.9714285714285714 Epoch: 4980 | Loss: 0.19670564641103802 | Accuracy: 0.9714285714285714 Epoch: 4981 | Loss: 0.19668648385978627 | Accuracy: 0.9714285714285714 Epoch: 4982 | Loss: 0.19666732707900758 | Accuracy: 0.9714285714285714 Epoch: 4983 | Loss: 0.19664817606607046 | Accuracy: 0.9714285714285714 Epoch: 4984 | Loss: 0.19662903081834499 | Accuracy: 0.9714285714285714 Epoch: 4985 | Loss: 0.19660989133320297 | Accuracy: 0.9714285714285714 Epoch: 4986 | Loss: 0.19659075760801759 | Accuracy: 0.9714285714285714 Epoch: 4987 | Loss: 0.19657162964016375 | Accuracy: 0.9714285714285714 Epoch: 4988 | Loss: 0.196552507427018 | Accuracy: 0.9714285714285714 Epoch: 4989 | Loss: 0.19653339096595826 | Accuracy: 0.9714285714285714 Epoch: 4990 | Loss: 0.19651428025436415 | Accuracy: 0.9714285714285714 Epoch: 4991 | Loss: 0.19649517528961685 | Accuracy: 0.9714285714285714 Epoch: 4992 | Loss: 0.19647607606909925 | Accuracy: 0.9714285714285714 Epoch: 4993 | Loss: 0.19645698259019553 | Accuracy: 0.9714285714285714 Epoch: 4994 | Loss: 0.19643789485029178 | Accuracy: 0.9714285714285714 Epoch: 4995 | Loss: 0.19641881284677545 | Accuracy: 0.9714285714285714 Epoch: 4996 | Loss: 0.19639973657703555 | Accuracy: 0.9714285714285714 Epoch: 4997 | Loss: 0.19638066603846283 | Accuracy: 0.9714285714285714 Epoch: 4998 | Loss: 0.1963616012284494 | Accuracy: 0.9714285714285714 Epoch: 4999 | Loss: 0.1963425421443892 | Accuracy: 0.9714285714285714 Epoch: 5000 | Loss: 0.19632348878367745 | Accuracy: 0.9714285714285714
calculate_accuracy(model(X_test), y_test)
0.9777777777777777
model = nn.Sequential(
nn.Linear(4, 3),
)
optimizer = optim.SGD(model.parameters(), lr=1e-2)
criterion = nn.CrossEntropyLoss()
train_model_torch(torch.tensor(X_train).float(), torch.tensor(y_train).long(), model, optimizer, criterion, 5000)
: 0.19455954432487488 | Accuracy: 0.9714285731315613 Epoch: 4719 | Loss: 0.19453993439674377 | Accuracy: 0.9714285731315613 Epoch: 4720 | Loss: 0.1945202648639679 | Accuracy: 0.9714285731315613 Epoch: 4721 | Loss: 0.19450058043003082 | Accuracy: 0.9714285731315613 Epoch: 4722 | Loss: 0.19448089599609375 | Accuracy: 0.9714285731315613 Epoch: 4723 | Loss: 0.19446127116680145 | Accuracy: 0.9714285731315613 Epoch: 4724 | Loss: 0.19444169104099274 | Accuracy: 0.9714285731315613 Epoch: 4725 | Loss: 0.19442208111286163 | Accuracy: 0.9714285731315613 Epoch: 4726 | Loss: 0.19440235197544098 | Accuracy: 0.9714285731315613 Epoch: 4727 | Loss: 0.19438280165195465 | Accuracy: 0.9714285731315613 Epoch: 4728 | Loss: 0.19436323642730713 | Accuracy: 0.9714285731315613 Epoch: 4729 | Loss: 0.19434362649917603 | Accuracy: 0.9714285731315613 Epoch: 4730 | Loss: 0.1943240761756897 | Accuracy: 0.9714285731315613 Epoch: 4731 | Loss: 0.1943044513463974 | Accuracy: 0.9714285731315613 Epoch: 4732 | Loss: 0.1942848265171051 | Accuracy: 0.9714285731315613 Epoch: 4733 | Loss: 0.19426527619361877 | Accuracy: 0.9714285731315613 Epoch: 4734 | Loss: 0.19424565136432648 | Accuracy: 0.9714285731315613 Epoch: 4735 | Loss: 0.19422614574432373 | Accuracy: 0.9714285731315613 Epoch: 4736 | Loss: 0.19420655071735382 | Accuracy: 0.9714285731315613 Epoch: 4737 | Loss: 0.1941869854927063 | Accuracy: 0.9714285731315613 Epoch: 4738 | Loss: 0.19416747987270355 | Accuracy: 0.9714285731315613 Epoch: 4739 | Loss: 0.1941479593515396 | Accuracy: 0.9714285731315613 Epoch: 4740 | Loss: 0.1941283941268921 | Accuracy: 0.9714285731315613 Epoch: 4741 | Loss: 0.19410890340805054 | Accuracy: 0.9714285731315613 Epoch: 4742 | Loss: 0.19408941268920898 | Accuracy: 0.9714285731315613 Epoch: 4743 | Loss: 0.19406984746456146 | Accuracy: 0.9714285731315613 Epoch: 4744 | Loss: 0.19405032694339752 | Accuracy: 0.9714285731315613 Epoch: 4745 | Loss: 0.19403076171875 | Accuracy: 0.9714285731315613 Epoch: 4746 | Loss: 0.19401130080223083 | Accuracy: 0.9714285731315613 Epoch: 4747 | Loss: 0.19399186968803406 | Accuracy: 0.9714285731315613 Epoch: 4748 | Loss: 0.1939723938703537 | Accuracy: 0.9714285731315613 Epoch: 4749 | Loss: 0.19395290315151215 | Accuracy: 0.9714285731315613 Epoch: 4750 | Loss: 0.19393348693847656 | Accuracy: 0.9714285731315613 Epoch: 4751 | Loss: 0.1939140111207962 | Accuracy: 0.9714285731315613 Epoch: 4752 | Loss: 0.19389449059963226 | Accuracy: 0.9714285731315613 Epoch: 4753 | Loss: 0.1938750296831131 | Accuracy: 0.9714285731315613 Epoch: 4754 | Loss: 0.19385558366775513 | Accuracy: 0.9714285731315613 Epoch: 4755 | Loss: 0.19383615255355835 | Accuracy: 0.9714285731315613 Epoch: 4756 | Loss: 0.19381675124168396 | Accuracy: 0.9714285731315613 Epoch: 4757 | Loss: 0.19379734992980957 | Accuracy: 0.9714285731315613 Epoch: 4758 | Loss: 0.1937779188156128 | Accuracy: 0.9714285731315613 Epoch: 4759 | Loss: 0.1937585026025772 | Accuracy: 0.9714285731315613 Epoch: 4760 | Loss: 0.1937391608953476 | Accuracy: 0.9714285731315613 Epoch: 4761 | Loss: 0.19371964037418365 | Accuracy: 0.9714285731315613 Epoch: 4762 | Loss: 0.19370035827159882 | Accuracy: 0.9714285731315613 Epoch: 4763 | Loss: 0.19368097186088562 | Accuracy: 0.9714285731315613 Epoch: 4764 | Loss: 0.19366155564785004 | Accuracy: 0.9714285731315613 Epoch: 4765 | Loss: 0.19364218413829803 | Accuracy: 0.9714285731315613 Epoch: 4766 | Loss: 0.19362284243106842 | Accuracy: 0.9714285731315613 Epoch: 4767 | Loss: 0.19360341131687164 | Accuracy: 0.9714285731315613 Epoch: 4768 | Loss: 0.19358409941196442 | Accuracy: 0.9714285731315613 Epoch: 4769 | Loss: 0.1935647577047348 | Accuracy: 0.9714285731315613 Epoch: 4770 | Loss: 0.1935454159975052 | Accuracy: 0.9714285731315613 Epoch: 4771 | Loss: 0.19352608919143677 | Accuracy: 0.9714285731315613 Epoch: 4772 | Loss: 0.19350676238536835 | Accuracy: 0.9714285731315613 Epoch: 4773 | Loss: 0.1934874802827835 | Accuracy: 0.9714285731315613 Epoch: 4774 | Loss: 0.1934681087732315 | Accuracy: 0.9714285731315613 Epoch: 4775 | Loss: 0.1934487521648407 | Accuracy: 0.9714285731315613 Epoch: 4776 | Loss: 0.19342945516109467 | Accuracy: 0.9714285731315613 Epoch: 4777 | Loss: 0.19341020286083221 | Accuracy: 0.9714285731315613 Epoch: 4778 | Loss: 0.19339096546173096 | Accuracy: 0.9714285731315613 Epoch: 4779 | Loss: 0.19337163865566254 | Accuracy: 0.9714285731315613 Epoch: 4780 | Loss: 0.19335231184959412 | Accuracy: 0.9714285731315613 Epoch: 4781 | Loss: 0.19333301484584808 | Accuracy: 0.9714285731315613 Epoch: 4782 | Loss: 0.19331377744674683 | Accuracy: 0.9714285731315613 Epoch: 4783 | Loss: 0.193294495344162 | Accuracy: 0.9714285731315613 Epoch: 4784 | Loss: 0.19327525794506073 | Accuracy: 0.9714285731315613 Epoch: 4785 | Loss: 0.19325603544712067 | Accuracy: 0.9714285731315613 Epoch: 4786 | Loss: 0.1932368278503418 | Accuracy: 0.9714285731315613 Epoch: 4787 | Loss: 0.19321750104427338 | Accuracy: 0.9714285731315613 Epoch: 4788 | Loss: 0.19319835305213928 | Accuracy: 0.9714285731315613 Epoch: 4789 | Loss: 0.19317908585071564 | Accuracy: 0.9714285731315613 Epoch: 4790 | Loss: 0.19315987825393677 | Accuracy: 0.9714285731315613 Epoch: 4791 | Loss: 0.1931406706571579 | Accuracy: 0.9714285731315613 Epoch: 4792 | Loss: 0.19312143325805664 | Accuracy: 0.9714285731315613 Epoch: 4793 | Loss: 0.19310224056243896 | Accuracy: 0.9714285731315613 Epoch: 4794 | Loss: 0.19308312237262726 | Accuracy: 0.9714285731315613 Epoch: 4795 | Loss: 0.1930638700723648 | Accuracy: 0.9714285731315613 Epoch: 4796 | Loss: 0.19304469227790833 | Accuracy: 0.9714285731315613 Epoch: 4797 | Loss: 0.19302555918693542 | Accuracy: 0.9714285731315613 Epoch: 4798 | Loss: 0.19300633668899536 | Accuracy: 0.9714285731315613 Epoch: 4799 | Loss: 0.19298717379570007 | Accuracy: 0.9714285731315613 Epoch: 4800 | Loss: 0.19296807050704956 | Accuracy: 0.9714285731315613 Epoch: 4801 | Loss: 0.19294887781143188 | Accuracy: 0.9714285731315613 Epoch: 4802 | Loss: 0.1929297149181366 | Accuracy: 0.9714285731315613 Epoch: 4803 | Loss: 0.19291062653064728 | Accuracy: 0.9714285731315613 Epoch: 4804 | Loss: 0.19289147853851318 | Accuracy: 0.9714285731315613 Epoch: 4805 | Loss: 0.1928722858428955 | Accuracy: 0.9714285731315613 Epoch: 4806 | Loss: 0.19285321235656738 | Accuracy: 0.9714285731315613 Epoch: 4807 | Loss: 0.19283409416675568 | Accuracy: 0.9714285731315613 Epoch: 4808 | Loss: 0.19281502068042755 | Accuracy: 0.9714285731315613 Epoch: 4809 | Loss: 0.19279585778713226 | Accuracy: 0.9714285731315613 Epoch: 4810 | Loss: 0.19277681410312653 | Accuracy: 0.9714285731315613 Epoch: 4811 | Loss: 0.192757710814476 | Accuracy: 0.9714285731315613 Epoch: 4812 | Loss: 0.1927386373281479 | Accuracy: 0.9714285731315613 Epoch: 4813 | Loss: 0.19271953403949738 | Accuracy: 0.9714285731315613 Epoch: 4814 | Loss: 0.19270049035549164 | Accuracy: 0.9714285731315613 Epoch: 4815 | Loss: 0.1926814168691635 | Accuracy: 0.9714285731315613 Epoch: 4816 | Loss: 0.19266241788864136 | Accuracy: 0.9714285731315613 Epoch: 4817 | Loss: 0.19264329969882965 | Accuracy: 0.9714285731315613 Epoch: 4818 | Loss: 0.1926243007183075 | Accuracy: 0.9714285731315613 Epoch: 4819 | Loss: 0.19260519742965698 | Accuracy: 0.9714285731315613 Epoch: 4820 | Loss: 0.19258621335029602 | Accuracy: 0.9714285731315613 Epoch: 4821 | Loss: 0.1925671547651291 | Accuracy: 0.9714285731315613 Epoch: 4822 | Loss: 0.19254815578460693 | Accuracy: 0.9714285731315613 Epoch: 4823 | Loss: 0.1925291121006012 | Accuracy: 0.9714285731315613 Epoch: 4824 | Loss: 0.19251009821891785 | Accuracy: 0.9714285731315613 Epoch: 4825 | Loss: 0.19249117374420166 | Accuracy: 0.9714285731315613 Epoch: 4826 | Loss: 0.19247211515903473 | Accuracy: 0.9714285731315613 Epoch: 4827 | Loss: 0.19245308637619019 | Accuracy: 0.9714285731315613 Epoch: 4828 | Loss: 0.192434161901474 | Accuracy: 0.9714285731315613 Epoch: 4829 | Loss: 0.19241516292095184 | Accuracy: 0.9714285731315613 Epoch: 4830 | Loss: 0.19239619374275208 | Accuracy: 0.9714285731315613 Epoch: 4831 | Loss: 0.1923772245645523 | Accuracy: 0.9714285731315613 Epoch: 4832 | Loss: 0.19235828518867493 | Accuracy: 0.9714285731315613 Epoch: 4833 | Loss: 0.19233933091163635 | Accuracy: 0.9714285731315613 Epoch: 4834 | Loss: 0.19232036173343658 | Accuracy: 0.9714285731315613 Epoch: 4835 | Loss: 0.1923014372587204 | Accuracy: 0.9714285731315613 Epoch: 4836 | Loss: 0.19228248298168182 | Accuracy: 0.9714285731315613 Epoch: 4837 | Loss: 0.1922636181116104 | Accuracy: 0.9714285731315613 Epoch: 4838 | Loss: 0.19224460422992706 | Accuracy: 0.9714285731315613 Epoch: 4839 | Loss: 0.19222573935985565 | Accuracy: 0.9714285731315613 Epoch: 4840 | Loss: 0.19220678508281708 | Accuracy: 0.9714285731315613 Epoch: 4841 | Loss: 0.19218799471855164 | Accuracy: 0.9714285731315613 Epoch: 4842 | Loss: 0.19216901063919067 | Accuracy: 0.9714285731315613 Epoch: 4843 | Loss: 0.19215011596679688 | Accuracy: 0.9714285731315613 Epoch: 4844 | Loss: 0.1921311467885971 | Accuracy: 0.9714285731315613 Epoch: 4845 | Loss: 0.19211235642433167 | Accuracy: 0.9714285731315613 Epoch: 4846 | Loss: 0.19209347665309906 | Accuracy: 0.9714285731315613 Epoch: 4847 | Loss: 0.19207456707954407 | Accuracy: 0.9714285731315613 Epoch: 4848 | Loss: 0.19205574691295624 | Accuracy: 0.9714285731315613 Epoch: 4849 | Loss: 0.19203683733940125 | Accuracy: 0.9714285731315613 Epoch: 4850 | Loss: 0.19201800227165222 | Accuracy: 0.9714285731315613 Epoch: 4851 | Loss: 0.1919991672039032 | Accuracy: 0.9714285731315613 Epoch: 4852 | Loss: 0.19198034703731537 | Accuracy: 0.9714285731315613 Epoch: 4853 | Loss: 0.19196145236492157 | Accuracy: 0.9714285731315613 Epoch: 4854 | Loss: 0.19194269180297852 | Accuracy: 0.9714285731315613 Epoch: 4855 | Loss: 0.1919238269329071 | Accuracy: 0.9714285731315613 Epoch: 4856 | Loss: 0.19190503656864166 | Accuracy: 0.9714285731315613 Epoch: 4857 | Loss: 0.19188624620437622 | Accuracy: 0.9714285731315613 Epoch: 4858 | Loss: 0.19186744093894958 | Accuracy: 0.9714285731315613 Epoch: 4859 | Loss: 0.19184865057468414 | Accuracy: 0.9714285731315613 Epoch: 4860 | Loss: 0.19182981550693512 | Accuracy: 0.9714285731315613 Epoch: 4861 | Loss: 0.19181108474731445 | Accuracy: 0.9714285731315613 Epoch: 4862 | Loss: 0.19179224967956543 | Accuracy: 0.9714285731315613 Epoch: 4863 | Loss: 0.19177348911762238 | Accuracy: 0.9714285731315613 Epoch: 4864 | Loss: 0.19175469875335693 | Accuracy: 0.9714285731315613 Epoch: 4865 | Loss: 0.19173595309257507 | Accuracy: 0.9714285731315613 Epoch: 4866 | Loss: 0.1917172372341156 | Accuracy: 0.9714285731315613 Epoch: 4867 | Loss: 0.19169847667217255 | Accuracy: 0.9714285731315613 Epoch: 4868 | Loss: 0.1916797161102295 | Accuracy: 0.9714285731315613 Epoch: 4869 | Loss: 0.19166098535060883 | Accuracy: 0.9714285731315613 Epoch: 4870 | Loss: 0.19164223968982697 | Accuracy: 0.9714285731315613 Epoch: 4871 | Loss: 0.1916235089302063 | Accuracy: 0.9714285731315613 Epoch: 4872 | Loss: 0.1916048377752304 | Accuracy: 0.9714285731315613 Epoch: 4873 | Loss: 0.19158604741096497 | Accuracy: 0.9714285731315613 Epoch: 4874 | Loss: 0.19156737625598907 | Accuracy: 0.9714285731315613 Epoch: 4875 | Loss: 0.19154863059520721 | Accuracy: 0.9714285731315613 Epoch: 4876 | Loss: 0.19152989983558655 | Accuracy: 0.9714285731315613 Epoch: 4877 | Loss: 0.19151130318641663 | Accuracy: 0.9714285731315613 Epoch: 4878 | Loss: 0.19149266183376312 | Accuracy: 0.9714285731315613 Epoch: 4879 | Loss: 0.19147391617298126 | Accuracy: 0.9714285731315613 Epoch: 4880 | Loss: 0.19145524501800537 | Accuracy: 0.9714285731315613 Epoch: 4881 | Loss: 0.19143660366535187 | Accuracy: 0.9714285731315613 Epoch: 4882 | Loss: 0.19141800701618195 | Accuracy: 0.9714285731315613 Epoch: 4883 | Loss: 0.19139929115772247 | Accuracy: 0.9714285731315613 Epoch: 4884 | Loss: 0.1913806051015854 | Accuracy: 0.9714285731315613 Epoch: 4885 | Loss: 0.19136196374893188 | Accuracy: 0.9714285731315613 Epoch: 4886 | Loss: 0.1913433074951172 | Accuracy: 0.9714285731315613 Epoch: 4887 | Loss: 0.19132471084594727 | Accuracy: 0.9714285731315613 Epoch: 4888 | Loss: 0.19130605459213257 | Accuracy: 0.9714285731315613 Epoch: 4889 | Loss: 0.19128742814064026 | Accuracy: 0.9714285731315613 Epoch: 4890 | Loss: 0.19126881659030914 | Accuracy: 0.9714285731315613 Epoch: 4891 | Loss: 0.1912502497434616 | Accuracy: 0.9714285731315613 Epoch: 4892 | Loss: 0.1912316083908081 | Accuracy: 0.9714285731315613 Epoch: 4893 | Loss: 0.19121305644512177 | Accuracy: 0.9714285731315613 Epoch: 4894 | Loss: 0.19119444489479065 | Accuracy: 0.9714285731315613 Epoch: 4895 | Loss: 0.19117581844329834 | Accuracy: 0.9714285731315613 Epoch: 4896 | Loss: 0.19115732610225677 | Accuracy: 0.9714285731315613 Epoch: 4897 | Loss: 0.19113869965076447 | Accuracy: 0.9714285731315613 Epoch: 4898 | Loss: 0.19112016260623932 | Accuracy: 0.9714285731315613 Epoch: 4899 | Loss: 0.19110159575939178 | Accuracy: 0.9714285731315613 Epoch: 4900 | Loss: 0.19108302891254425 | Accuracy: 0.9714285731315613 Epoch: 4901 | Loss: 0.1910644918680191 | Accuracy: 0.9714285731315613 Epoch: 4902 | Loss: 0.19104592502117157 | Accuracy: 0.9714285731315613 Epoch: 4903 | Loss: 0.19102737307548523 | Accuracy: 0.9714285731315613 Epoch: 4904 | Loss: 0.19100886583328247 | Accuracy: 0.9714285731315613 Epoch: 4905 | Loss: 0.19099031388759613 | Accuracy: 0.9714285731315613 Epoch: 4906 | Loss: 0.19097185134887695 | Accuracy: 0.9714285731315613 Epoch: 4907 | Loss: 0.1909533590078354 | Accuracy: 0.9714285731315613 Epoch: 4908 | Loss: 0.19093483686447144 | Accuracy: 0.9714285731315613 Epoch: 4909 | Loss: 0.1909162849187851 | Accuracy: 0.9714285731315613 Epoch: 4910 | Loss: 0.19089780747890472 | Accuracy: 0.9714285731315613 Epoch: 4911 | Loss: 0.19087930023670197 | Accuracy: 0.9714285731315613 Epoch: 4912 | Loss: 0.1908608227968216 | Accuracy: 0.9714285731315613 Epoch: 4913 | Loss: 0.1908424198627472 | Accuracy: 0.9714285731315613 Epoch: 4914 | Loss: 0.19082386791706085 | Accuracy: 0.9714285731315613 Epoch: 4915 | Loss: 0.19080540537834167 | Accuracy: 0.9714285731315613 Epoch: 4916 | Loss: 0.1907869130373001 | Accuracy: 0.9714285731315613 Epoch: 4917 | Loss: 0.19076843559741974 | Accuracy: 0.9714285731315613 Epoch: 4918 | Loss: 0.19075006246566772 | Accuracy: 0.9714285731315613 Epoch: 4919 | Loss: 0.19073162972927094 | Accuracy: 0.9714285731315613 Epoch: 4920 | Loss: 0.19071313738822937 | Accuracy: 0.9714285731315613 Epoch: 4921 | Loss: 0.19069471955299377 | Accuracy: 0.9714285731315613 Epoch: 4922 | Loss: 0.19067633152008057 | Accuracy: 0.9714285731315613 Epoch: 4923 | Loss: 0.19065789878368378 | Accuracy: 0.9714285731315613 Epoch: 4924 | Loss: 0.1906394362449646 | Accuracy: 0.9714285731315613 Epoch: 4925 | Loss: 0.19062106311321259 | Accuracy: 0.9714285731315613 Epoch: 4926 | Loss: 0.19060270488262177 | Accuracy: 0.9714285731315613 Epoch: 4927 | Loss: 0.19058431684970856 | Accuracy: 0.9714285731315613 Epoch: 4928 | Loss: 0.19056588411331177 | Accuracy: 0.9714285731315613 Epoch: 4929 | Loss: 0.19054746627807617 | Accuracy: 0.9714285731315613 Epoch: 4930 | Loss: 0.19052910804748535 | Accuracy: 0.9714285731315613 Epoch: 4931 | Loss: 0.19051077961921692 | Accuracy: 0.9714285731315613 Epoch: 4932 | Loss: 0.1904924064874649 | Accuracy: 0.9714285731315613 Epoch: 4933 | Loss: 0.1904739886522293 | Accuracy: 0.9714285731315613 Epoch: 4934 | Loss: 0.1904556304216385 | Accuracy: 0.9714285731315613 Epoch: 4935 | Loss: 0.19043733179569244 | Accuracy: 0.9714285731315613 Epoch: 4936 | Loss: 0.19041891396045685 | Accuracy: 0.9714285731315613 Epoch: 4937 | Loss: 0.1904006004333496 | Accuracy: 0.9714285731315613 Epoch: 4938 | Loss: 0.19038227200508118 | Accuracy: 0.9714285731315613 Epoch: 4939 | Loss: 0.19036389887332916 | Accuracy: 0.9714285731315613 Epoch: 4940 | Loss: 0.19034560024738312 | Accuracy: 0.9714285731315613 Epoch: 4941 | Loss: 0.19032728672027588 | Accuracy: 0.9714285731315613 Epoch: 4942 | Loss: 0.19030903279781342 | Accuracy: 0.9714285731315613 Epoch: 4943 | Loss: 0.19029076397418976 | Accuracy: 0.9714285731315613 Epoch: 4944 | Loss: 0.19027240574359894 | Accuracy: 0.9714285731315613 Epoch: 4945 | Loss: 0.19025415182113647 | Accuracy: 0.9714285731315613 Epoch: 4946 | Loss: 0.19023582339286804 | Accuracy: 0.9714285731315613 Epoch: 4947 | Loss: 0.1902174949645996 | Accuracy: 0.9714285731315613 Epoch: 4948 | Loss: 0.19019924104213715 | Accuracy: 0.9714285731315613 Epoch: 4949 | Loss: 0.1901809722185135 | Accuracy: 0.9714285731315613 Epoch: 4950 | Loss: 0.19016273319721222 | Accuracy: 0.9714285731315613 Epoch: 4951 | Loss: 0.19014443457126617 | Accuracy: 0.9714285731315613 Epoch: 4952 | Loss: 0.1901262253522873 | Accuracy: 0.9714285731315613 Epoch: 4953 | Loss: 0.19010794162750244 | Accuracy: 0.9714285731315613 Epoch: 4954 | Loss: 0.19008968770503998 | Accuracy: 0.9714285731315613 Epoch: 4955 | Loss: 0.1900714933872223 | Accuracy: 0.9714285731315613 Epoch: 4956 | Loss: 0.19005322456359863 | Accuracy: 0.9714285731315613 Epoch: 4957 | Loss: 0.19003501534461975 | Accuracy: 0.9714285731315613 Epoch: 4958 | Loss: 0.19001685082912445 | Accuracy: 0.9714285731315613 Epoch: 4959 | Loss: 0.1899985671043396 | Accuracy: 0.9714285731315613 Epoch: 4960 | Loss: 0.1899803876876831 | Accuracy: 0.9714285731315613 Epoch: 4961 | Loss: 0.18996216356754303 | Accuracy: 0.9714285731315613 Epoch: 4962 | Loss: 0.18994402885437012 | Accuracy: 0.9714285731315613 Epoch: 4963 | Loss: 0.18992581963539124 | Accuracy: 0.9714285731315613 Epoch: 4964 | Loss: 0.18990762531757355 | Accuracy: 0.9714285731315613 Epoch: 4965 | Loss: 0.18988940119743347 | Accuracy: 0.9714285731315613 Epoch: 4966 | Loss: 0.18987122178077698 | Accuracy: 0.9714285731315613 Epoch: 4967 | Loss: 0.18985308706760406 | Accuracy: 0.9714285731315613 Epoch: 4968 | Loss: 0.18983492255210876 | Accuracy: 0.9714285731315613 Epoch: 4969 | Loss: 0.18981683254241943 | Accuracy: 0.9714285731315613 Epoch: 4970 | Loss: 0.18979860842227936 | Accuracy: 0.9714285731315613 Epoch: 4971 | Loss: 0.18978047370910645 | Accuracy: 0.9714285731315613 Epoch: 4972 | Loss: 0.18976233899593353 | Accuracy: 0.9714285731315613 Epoch: 4973 | Loss: 0.18974421918392181 | Accuracy: 0.9714285731315613 Epoch: 4974 | Loss: 0.1897261142730713 | Accuracy: 0.9714285731315613 Epoch: 4975 | Loss: 0.1897079348564148 | Accuracy: 0.9714285731315613 Epoch: 4976 | Loss: 0.18968981504440308 | Accuracy: 0.9714285731315613 Epoch: 4977 | Loss: 0.18967172503471375 | Accuracy: 0.9714285731315613 Epoch: 4978 | Loss: 0.18965363502502441 | Accuracy: 0.9714285731315613 Epoch: 4979 | Loss: 0.18963554501533508 | Accuracy: 0.9714285731315613 Epoch: 4980 | Loss: 0.18961741030216217 | Accuracy: 0.9714285731315613 Epoch: 4981 | Loss: 0.18959933519363403 | Accuracy: 0.9714285731315613 Epoch: 4982 | Loss: 0.1895812749862671 | Accuracy: 0.9714285731315613 Epoch: 4983 | Loss: 0.18956317007541656 | Accuracy: 0.9714285731315613 Epoch: 4984 | Loss: 0.18954506516456604 | Accuracy: 0.9714285731315613 Epoch: 4985 | Loss: 0.18952706456184387 | Accuracy: 0.9714285731315613 Epoch: 4986 | Loss: 0.18950900435447693 | Accuracy: 0.9714285731315613 Epoch: 4987 | Loss: 0.1894909143447876 | Accuracy: 0.9714285731315613 Epoch: 4988 | Loss: 0.18947286903858185 | Accuracy: 0.9714285731315613 Epoch: 4989 | Loss: 0.1894548535346985 | Accuracy: 0.9714285731315613 Epoch: 4990 | Loss: 0.18943680822849274 | Accuracy: 0.9714285731315613 Epoch: 4991 | Loss: 0.1894187331199646 | Accuracy: 0.9714285731315613 Epoch: 4992 | Loss: 0.18940074741840363 | Accuracy: 0.9714285731315613 Epoch: 4993 | Loss: 0.18938270211219788 | Accuracy: 0.9714285731315613 Epoch: 4994 | Loss: 0.1893647164106369 | Accuracy: 0.9714285731315613 Epoch: 4995 | Loss: 0.18934670090675354 | Accuracy: 0.9714285731315613 Epoch: 4996 | Loss: 0.18932870030403137 | Accuracy: 0.9714285731315613 Epoch: 4997 | Loss: 0.18931065499782562 | Accuracy: 0.9714285731315613 Epoch: 4998 | Loss: 0.18929272890090942 | Accuracy: 0.9714285731315613 Epoch: 4999 | Loss: 0.18927472829818726 | Accuracy: 0.9714285731315613 Epoch: 5000 | Loss: 0.18925675749778748 | Accuracy: 0.9714285731315613
calculate_accuracy_torch(model(torch.tensor(X_test).float()), torch.tensor(y_test).long()).item()
0.9777777791023254
def colored_dots(y):
colors = ("red", "blue")
colored_y = np.zeros(y.size, dtype=str)
for i, cl in enumerate([0,1]):
colored_y[y == cl] = str(colors[i])
return colored_y
def plot_graph(X, y):
plt.figure(figsize=(15,10))
plt.scatter(X[:, 0], X[:, 1], c=colored_dots(y))
plt.show()
def plot_colored_graph(model, X, y, eps=0.1):
plt.figure(figsize=(15,8))
xx, yy = np.meshgrid(np.linspace(np.min(X[:,0]) - eps, np.max(X[:,0]) + eps, 200),
np.linspace(np.min(X[:,1]) - eps, np.max(X[:,1]) + eps, 200))
Z = np.argmax(model(np.c_[xx.ravel(), yy.ravel()]), axis=1)
Z = Z.reshape(xx.shape)
cmap_light = ListedColormap(['#FFAAAA', '#AAAAFF'])
plt.pcolormesh(xx, yy, Z, cmap=cmap_light)
plt.scatter(X[:, 0], X[:, 1], c=colored_dots(y))
X, y = np.array([[1, 0], [1, 1], [0, 1], [0, 0]]), np.array([1, 0, 0, 1])
plot_graph(X, y)
model = Sequential(
Linear(2, 2),
)
optimizer = SGD(model.parameters(), lr=5e-2, momentum=0.9)
criterion = CrossEntropyLoss()
train_model(X, y, model, optimizer, criterion, 700)
Accuracy: 1.0 Epoch: 343 | Loss: 0.014062056380827756 | Accuracy: 1.0 Epoch: 344 | Loss: 0.014022091979678153 | Accuracy: 1.0 Epoch: 345 | Loss: 0.013982355794338128 | Accuracy: 1.0 Epoch: 346 | Loss: 0.013942845864684405 | Accuracy: 1.0 Epoch: 347 | Loss: 0.013903560253080129 | Accuracy: 1.0 Epoch: 348 | Loss: 0.013864497044052009 | Accuracy: 1.0 Epoch: 349 | Loss: 0.013825654343973232 | Accuracy: 1.0 Epoch: 350 | Loss: 0.01378703028075131 | Accuracy: 1.0 Epoch: 351 | Loss: 0.013748623003521924 | Accuracy: 1.0 Epoch: 352 | Loss: 0.013710430682347475 | Accuracy: 1.0 Epoch: 353 | Loss: 0.013672451507920834 | Accuracy: 1.0 Epoch: 354 | Loss: 0.013634683691274898 | Accuracy: 1.0 Epoch: 355 | Loss: 0.013597125463495535 | Accuracy: 1.0 Epoch: 356 | Loss: 0.013559775075441169 | Accuracy: 1.0 Epoch: 357 | Loss: 0.013522630797465608 | Accuracy: 1.0 Epoch: 358 | Loss: 0.013485690919146351 | Accuracy: 1.0 Epoch: 359 | Loss: 0.013448953749017297 | Accuracy: 1.0 Epoch: 360 | Loss: 0.013412417614305656 | Accuracy: 1.0 Epoch: 361 | Loss: 0.013376080860673514 | Accuracy: 1.0 Epoch: 362 | Loss: 0.013339941851963629 | Accuracy: 1.0 Epoch: 363 | Loss: 0.01330399896994954 | Accuracy: 1.0 Epoch: 364 | Loss: 0.013268250614089233 | Accuracy: 1.0 Epoch: 365 | Loss: 0.013232695201283923 | Accuracy: 1.0 Epoch: 366 | Loss: 0.01319733116563955 | Accuracy: 1.0 Epoch: 367 | Loss: 0.013162156958233593 | Accuracy: 1.0 Epoch: 368 | Loss: 0.013127171046883846 | Accuracy: 1.0 Epoch: 369 | Loss: 0.013092371915923127 | Accuracy: 1.0 Epoch: 370 | Loss: 0.013057758065975759 | Accuracy: 1.0 Epoch: 371 | Loss: 0.013023328013738915 | Accuracy: 1.0 Epoch: 372 | Loss: 0.012989080291766576 | Accuracy: 1.0 Epoch: 373 | Loss: 0.0129550134482581 | Accuracy: 1.0 Epoch: 374 | Loss: 0.01292112604684877 | Accuracy: 1.0 Epoch: 375 | Loss: 0.012887416666405202 | Accuracy: 1.0 Epoch: 376 | Loss: 0.012853883900822234 | Accuracy: 1.0 Epoch: 377 | Loss: 0.01282052635882519 | Accuracy: 1.0 Epoch: 378 | Loss: 0.012787342663773587 | Accuracy: 1.0 Epoch: 379 | Loss: 0.012754331453468656 | Accuracy: 1.0 Epoch: 380 | Loss: 0.012721491379963467 | Accuracy: 1.0 Epoch: 381 | Loss: 0.012688821109377035 | Accuracy: 1.0 Epoch: 382 | Loss: 0.012656319321710028 | Accuracy: 1.0 Epoch: 383 | Loss: 0.012623984710664636 | Accuracy: 1.0 Epoch: 384 | Loss: 0.01259181598346586 | Accuracy: 1.0 Epoch: 385 | Loss: 0.012559811860687081 | Accuracy: 1.0 Epoch: 386 | Loss: 0.012527971076077123 | Accuracy: 1.0 Epoch: 387 | Loss: 0.012496292376391105 | Accuracy: 1.0 Epoch: 388 | Loss: 0.012464774521222551 | Accuracy: 1.0 Epoch: 389 | Loss: 0.012433416282839223 | Accuracy: 1.0 Epoch: 390 | Loss: 0.01240221644602136 | Accuracy: 1.0 Epoch: 391 | Loss: 0.01237117380790151 | Accuracy: 1.0 Epoch: 392 | Loss: 0.012340287177808187 | Accuracy: 1.0 Epoch: 393 | Loss: 0.012309555377110315 | Accuracy: 1.0 Epoch: 394 | Loss: 0.01227897723906598 | Accuracy: 1.0 Epoch: 395 | Loss: 0.012248551608671157 | Accuracy: 1.0 Epoch: 396 | Loss: 0.012218277342513071 | Accuracy: 1.0 Epoch: 397 | Loss: 0.012188153308623849 | Accuracy: 1.0 Epoch: 398 | Loss: 0.012158178386337903 | Accuracy: 1.0 Epoch: 399 | Loss: 0.012128351466150189 | Accuracy: 1.0 Epoch: 400 | Loss: 0.012098671449577443 | Accuracy: 1.0 Epoch: 401 | Loss: 0.012069137249021141 | Accuracy: 1.0 Epoch: 402 | Loss: 0.012039747787632504 | Accuracy: 1.0 Epoch: 403 | Loss: 0.012010501999179815 | Accuracy: 1.0 Epoch: 404 | Loss: 0.01198139882791728 | Accuracy: 1.0 Epoch: 405 | Loss: 0.011952437228455955 | Accuracy: 1.0 Epoch: 406 | Loss: 0.01192361616563676 | Accuracy: 1.0 Epoch: 407 | Loss: 0.011894934614405004 | Accuracy: 1.0 Epoch: 408 | Loss: 0.011866391559687946 | Accuracy: 1.0 Epoch: 409 | Loss: 0.01183798599627169 | Accuracy: 1.0 Epoch: 410 | Loss: 0.01180971692868257 | Accuracy: 1.0 Epoch: 411 | Loss: 0.011781583371068834 | Accuracy: 1.0 Epoch: 412 | Loss: 0.011753584347083634 | Accuracy: 1.0 Epoch: 413 | Loss: 0.011725718889771527 | Accuracy: 1.0 Epoch: 414 | Loss: 0.011697986041454542 | Accuracy: 1.0 Epoch: 415 | Loss: 0.01167038485362147 | Accuracy: 1.0 Epoch: 416 | Loss: 0.011642914386817436 | Accuracy: 1.0 Epoch: 417 | Loss: 0.011615573710536236 | Accuracy: 1.0 Epoch: 418 | Loss: 0.011588361903113768 | Accuracy: 1.0 Epoch: 419 | Loss: 0.011561278051622548 | Accuracy: 1.0 Epoch: 420 | Loss: 0.011534321251768283 | Accuracy: 1.0 Epoch: 421 | Loss: 0.01150749060778791 | Accuracy: 1.0 Epoch: 422 | Loss: 0.011480785232348885 | Accuracy: 1.0 Epoch: 423 | Loss: 0.011454204246449487 | Accuracy: 1.0 Epoch: 424 | Loss: 0.011427746779321613 | Accuracy: 1.0 Epoch: 425 | Loss: 0.011401411968333986 | Accuracy: 1.0 Epoch: 426 | Loss: 0.011375198958896994 | Accuracy: 1.0 Epoch: 427 | Loss: 0.011349106904369043 | Accuracy: 1.0 Epoch: 428 | Loss: 0.01132313496596423 | Accuracy: 1.0 Epoch: 429 | Loss: 0.011297282312660709 | Accuracy: 1.0 Epoch: 430 | Loss: 0.011271548121111155 | Accuracy: 1.0 Epoch: 431 | Loss: 0.011245931575554475 | Accuracy: 1.0 Epoch: 432 | Loss: 0.011220431867727384 | Accuracy: 1.0 Epoch: 433 | Loss: 0.011195048196779005 | Accuracy: 1.0 Epoch: 434 | Loss: 0.011169779769185748 | Accuracy: 1.0 Epoch: 435 | Loss: 0.01114462579866712 | Accuracy: 1.0 Epoch: 436 | Loss: 0.01111958550610341 | Accuracy: 1.0 Epoch: 437 | Loss: 0.011094658119453728 | Accuracy: 1.0 Epoch: 438 | Loss: 0.011069842873676019 | Accuracy: 1.0 Epoch: 439 | Loss: 0.011045139010647218 | Accuracy: 1.0 Epoch: 440 | Loss: 0.011020545779085506 | Accuracy: 1.0 Epoch: 441 | Loss: 0.010996062434472428 | Accuracy: 1.0 Epoch: 442 | Loss: 0.01097168823897754 | Accuracy: 1.0 Epoch: 443 | Loss: 0.010947422461382708 | Accuracy: 1.0 Epoch: 444 | Loss: 0.010923264377007972 | Accuracy: 1.0 Epoch: 445 | Loss: 0.010899213267638652 | Accuracy: 1.0 Epoch: 446 | Loss: 0.01087526842145335 | Accuracy: 1.0 Epoch: 447 | Loss: 0.010851429132952468 | Accuracy: 1.0 Epoch: 448 | Loss: 0.010827694702887797 | Accuracy: 1.0 Epoch: 449 | Loss: 0.010804064438193844 | Accuracy: 1.0 Epoch: 450 | Loss: 0.010780537651919062 | Accuracy: 1.0 Epoch: 451 | Loss: 0.010757113663158471 | Accuracy: 1.0 Epoch: 452 | Loss: 0.010733791796986742 | Accuracy: 1.0 Epoch: 453 | Loss: 0.010710571384393464 | Accuracy: 1.0 Epoch: 454 | Loss: 0.010687451762217248 | Accuracy: 1.0 Epoch: 455 | Loss: 0.0106644322730824 | Accuracy: 1.0 Epoch: 456 | Loss: 0.010641512265335504 | Accuracy: 1.0 Epoch: 457 | Loss: 0.010618691092983471 | Accuracy: 1.0 Epoch: 458 | Loss: 0.010595968115631689 | Accuracy: 1.0 Epoch: 459 | Loss: 0.010573342698423261 | Accuracy: 1.0 Epoch: 460 | Loss: 0.010550814211979537 | Accuracy: 1.0 Epoch: 461 | Loss: 0.010528382032340952 | Accuracy: 1.0 Epoch: 462 | Loss: 0.010506045540907978 | Accuracy: 1.0 Epoch: 463 | Loss: 0.010483804124384622 | Accuracy: 1.0 Epoch: 464 | Loss: 0.010461657174720574 | Accuracy: 1.0 Epoch: 465 | Loss: 0.01043960408905573 | Accuracy: 1.0 Epoch: 466 | Loss: 0.010417644269664468 | Accuracy: 1.0 Epoch: 467 | Loss: 0.01039577712390102 | Accuracy: 1.0 Epoch: 468 | Loss: 0.010374002064145686 | Accuracy: 1.0 Epoch: 469 | Loss: 0.010352318507751179 | Accuracy: 1.0 Epoch: 470 | Loss: 0.010330725876990207 | Accuracy: 1.0 Epoch: 471 | Loss: 0.010309223599003558 | Accuracy: 1.0 Epoch: 472 | Loss: 0.010287811105748678 | Accuracy: 1.0 Epoch: 473 | Loss: 0.010266487833949093 | Accuracy: 1.0 Epoch: 474 | Loss: 0.010245253225044366 | Accuracy: 1.0 Epoch: 475 | Loss: 0.01022410672514051 | Accuracy: 1.0 Epoch: 476 | Loss: 0.010203047784961804 | Accuracy: 1.0 Epoch: 477 | Loss: 0.010182075859802122 | Accuracy: 1.0 Epoch: 478 | Loss: 0.01016119040947764 | Accuracy: 1.0 Epoch: 479 | Loss: 0.010140390898279488 | Accuracy: 1.0 Epoch: 480 | Loss: 0.010119676794928062 | Accuracy: 1.0 Epoch: 481 | Loss: 0.010099047572526706 | Accuracy: 1.0 Epoch: 482 | Loss: 0.010078502708516499 | Accuracy: 1.0 Epoch: 483 | Loss: 0.010058041684631917 | Accuracy: 1.0 Epoch: 484 | Loss: 0.010037663986856517 | Accuracy: 1.0 Epoch: 485 | Loss: 0.01001736910537936 | Accuracy: 1.0 Epoch: 486 | Loss: 0.009997156534551991 | Accuracy: 1.0 Epoch: 487 | Loss: 0.00997702577284593 | Accuracy: 1.0 Epoch: 488 | Loss: 0.009956976322810862 | Accuracy: 1.0 Epoch: 489 | Loss: 0.009937007691033065 | Accuracy: 1.0 Epoch: 490 | Loss: 0.009917119388093969 | Accuracy: 1.0 Epoch: 491 | Loss: 0.009897310928530762 | Accuracy: 1.0 Epoch: 492 | Loss: 0.009877581830795241 | Accuracy: 1.0 Epoch: 493 | Loss: 0.009857931617215366 | Accuracy: 1.0 Epoch: 494 | Loss: 0.009838359813955245 | Accuracy: 1.0 Epoch: 495 | Loss: 0.009818865950977682 | Accuracy: 1.0 Epoch: 496 | Loss: 0.009799449562004976 | Accuracy: 1.0 Epoch: 497 | Loss: 0.0097801101844823 | Accuracy: 1.0 Epoch: 498 | Loss: 0.009760847359539927 | Accuracy: 1.0 Epoch: 499 | Loss: 0.009741660631956623 | Accuracy: 1.0 Epoch: 500 | Loss: 0.009722549550123602 | Accuracy: 1.0 Epoch: 501 | Loss: 0.009703513666008497 | Accuracy: 1.0 Epoch: 502 | Loss: 0.00968455253511988 | Accuracy: 1.0 Epoch: 503 | Loss: 0.009665665716472179 | Accuracy: 1.0 Epoch: 504 | Loss: 0.009646852772551687 | Accuracy: 1.0 Epoch: 505 | Loss: 0.009628113269281686 | Accuracy: 1.0 Epoch: 506 | Loss: 0.009609446775988852 | Accuracy: 1.0 Epoch: 507 | Loss: 0.009590852865370333 | Accuracy: 1.0 Epoch: 508 | Loss: 0.00957233111346012 | Accuracy: 1.0 Epoch: 509 | Loss: 0.00955388109959696 | Accuracy: 1.0 Epoch: 510 | Loss: 0.009535502406391748 | Accuracy: 1.0 Epoch: 511 | Loss: 0.00951719461969592 | Accuracy: 1.0 Epoch: 512 | Loss: 0.009498957328570323 | Accuracy: 1.0 Epoch: 513 | Loss: 0.009480790125253307 | Accuracy: 1.0 Epoch: 514 | Loss: 0.009462692605130666 | Accuracy: 1.0 Epoch: 515 | Loss: 0.009444664366705097 | Accuracy: 1.0 Epoch: 516 | Loss: 0.00942670501156599 | Accuracy: 1.0 Epoch: 517 | Loss: 0.009408814144359876 | Accuracy: 1.0 Epoch: 518 | Loss: 0.009390991372761295 | Accuracy: 1.0 Epoch: 519 | Loss: 0.009373236307443385 | Accuracy: 1.0 Epoch: 520 | Loss: 0.009355548562049565 | Accuracy: 1.0 Epoch: 521 | Loss: 0.009337927753165175 | Accuracy: 1.0 Epoch: 522 | Loss: 0.009320373500289098 | Accuracy: 1.0 Epoch: 523 | Loss: 0.00930288542580651 | Accuracy: 1.0 Epoch: 524 | Loss: 0.009285463154961432 | Accuracy: 1.0 Epoch: 525 | Loss: 0.0092681063158293 | Accuracy: 1.0 Epoch: 526 | Loss: 0.00925081453929076 | Accuracy: 1.0 Epoch: 527 | Loss: 0.009233587459004652 | Accuracy: 1.0 Epoch: 528 | Loss: 0.009216424711382398 | Accuracy: 1.0 Epoch: 529 | Loss: 0.009199325935561787 | Accuracy: 1.0 Epoch: 530 | Loss: 0.009182290773381493 | Accuracy: 1.0 Epoch: 531 | Loss: 0.009165318869355912 | Accuracy: 1.0 Epoch: 532 | Loss: 0.009148409870649937 | Accuracy: 1.0 Epoch: 533 | Loss: 0.009131563427054505 | Accuracy: 1.0 Epoch: 534 | Loss: 0.00911477919096182 | Accuracy: 1.0 Epoch: 535 | Loss: 0.009098056817341674 | Accuracy: 1.0 Epoch: 536 | Loss: 0.00908139596371708 | Accuracy: 1.0 Epoch: 537 | Loss: 0.00906479629014105 | Accuracy: 1.0 Epoch: 538 | Loss: 0.009048257459172811 | Accuracy: 1.0 Epoch: 539 | Loss: 0.009031779135854946 | Accuracy: 1.0 Epoch: 540 | Loss: 0.009015360987690657 | Accuracy: 1.0 Epoch: 541 | Loss: 0.008999002684620856 | Accuracy: 1.0 Epoch: 542 | Loss: 0.008982703899002065 | Accuracy: 1.0 Epoch: 543 | Loss: 0.008966464305584036 | Accuracy: 1.0 Epoch: 544 | Loss: 0.008950283581488354 | Accuracy: 1.0 Epoch: 545 | Loss: 0.00893416140618647 | Accuracy: 1.0 Epoch: 546 | Loss: 0.008918097461478062 | Accuracy: 1.0 Epoch: 547 | Loss: 0.008902091431470615 | Accuracy: 1.0 Epoch: 548 | Loss: 0.0088861430025579 | Accuracy: 1.0 Epoch: 549 | Loss: 0.008870251863399344 | Accuracy: 1.0 Epoch: 550 | Loss: 0.008854417704899968 | Accuracy: 1.0 Epoch: 551 | Loss: 0.008838640220189601 | Accuracy: 1.0 Epoch: 552 | Loss: 0.008822919104603082 | Accuracy: 1.0 Epoch: 553 | Loss: 0.00880725405566092 | Accuracy: 1.0 Epoch: 554 | Loss: 0.008791644773048717 | Accuracy: 1.0 Epoch: 555 | Loss: 0.008776090958598335 | Accuracy: 1.0 Epoch: 556 | Loss: 0.008760592316269064 | Accuracy: 1.0 Epoch: 557 | Loss: 0.008745148552128048 | Accuracy: 1.0 Epoch: 558 | Loss: 0.008729759374331784 | Accuracy: 1.0 Epoch: 559 | Loss: 0.008714424493107427 | Accuracy: 1.0 Epoch: 560 | Loss: 0.00869914362073465 | Accuracy: 1.0 Epoch: 561 | Loss: 0.008683916471527277 | Accuracy: 1.0 Epoch: 562 | Loss: 0.00866874276181524 | Accuracy: 1.0 Epoch: 563 | Loss: 0.008653622209927048 | Accuracy: 1.0 Epoch: 564 | Loss: 0.008638554536171836 | Accuracy: 1.0 Epoch: 565 | Loss: 0.00862353946282232 | Accuracy: 1.0 Epoch: 566 | Loss: 0.00860857671409746 | Accuracy: 1.0 Epoch: 567 | Loss: 0.00859366601614497 | Accuracy: 1.0 Epoch: 568 | Loss: 0.008578807097025246 | Accuracy: 1.0 Epoch: 569 | Loss: 0.008563999686693923 | Accuracy: 1.0 Epoch: 570 | Loss: 0.008549243516985678 | Accuracy: 1.0 Epoch: 571 | Loss: 0.008534538321598088 | Accuracy: 1.0 Epoch: 572 | Loss: 0.008519883836074948 | Accuracy: 1.0 Epoch: 573 | Loss: 0.008505279797790847 | Accuracy: 1.0 Epoch: 574 | Loss: 0.008490725945934852 | Accuracy: 1.0 Epoch: 575 | Loss: 0.008476222021494924 | Accuracy: 1.0 Epoch: 576 | Loss: 0.008461767767242556 | Accuracy: 1.0 Epoch: 577 | Loss: 0.008447362927717483 | Accuracy: 1.0 Epoch: 578 | Loss: 0.008433007249212202 | Accuracy: 1.0 Epoch: 579 | Loss: 0.008418700479757095 | Accuracy: 1.0 Epoch: 580 | Loss: 0.008404442369105605 | Accuracy: 1.0 Epoch: 581 | Loss: 0.008390232668719234 | Accuracy: 1.0 Epoch: 582 | Loss: 0.00837607113175334 | Accuracy: 1.0 Epoch: 583 | Loss: 0.00836195751304262 | Accuracy: 1.0 Epoch: 584 | Loss: 0.008347891569086484 | Accuracy: 1.0 Epoch: 585 | Loss: 0.008333873058035193 | Accuracy: 1.0 Epoch: 586 | Loss: 0.00831990173967606 | Accuracy: 1.0 Epoch: 587 | Loss: 0.008305977375419084 | Accuracy: 1.0 Epoch: 588 | Loss: 0.0082920997282838 | Accuracy: 1.0 Epoch: 589 | Loss: 0.008278268562885332 | Accuracy: 1.0 Epoch: 590 | Loss: 0.008264483645420822 | Accuracy: 1.0 Epoch: 591 | Loss: 0.008250744743656906 | Accuracy: 1.0 Epoch: 592 | Loss: 0.008237051626915504 | Accuracy: 1.0 Epoch: 593 | Loss: 0.008223404066061712 | Accuracy: 1.0 Epoch: 594 | Loss: 0.008209801833490123 | Accuracy: 1.0 Epoch: 595 | Loss: 0.008196244703112669 | Accuracy: 1.0 Epoch: 596 | Loss: 0.00818273245034559 | Accuracy: 1.0 Epoch: 597 | Loss: 0.008169264852097355 | Accuracy: 1.0 Epoch: 598 | Loss: 0.008155841686755582 | Accuracy: 1.0 Epoch: 599 | Loss: 0.008142462734175432 | Accuracy: 1.0 Epoch: 600 | Loss: 0.008129127775666947 | Accuracy: 1.0 Epoch: 601 | Loss: 0.008115836593983732 | Accuracy: 1.0 Epoch: 602 | Loss: 0.00810258897331005 | Accuracy: 1.0 Epoch: 603 | Loss: 0.00808938469924982 | Accuracy: 1.0 Epoch: 604 | Loss: 0.008076223558815009 | Accuracy: 1.0 Epoch: 605 | Loss: 0.00806310534041297 | Accuracy: 1.0 Epoch: 606 | Loss: 0.008050029833836632 | Accuracy: 1.0 Epoch: 607 | Loss: 0.008036996830251856 | Accuracy: 1.0 Epoch: 608 | Loss: 0.008024006122186868 | Accuracy: 1.0 Epoch: 609 | Loss: 0.008011057503520843 | Accuracy: 1.0 Epoch: 610 | Loss: 0.007998150769472977 | Accuracy: 1.0 Epoch: 611 | Loss: 0.007985285716592136 | Accuracy: 1.0 Epoch: 612 | Loss: 0.007972462142744934 | Accuracy: 1.0 Epoch: 613 | Loss: 0.007959679847106164 | Accuracy: 1.0 Epoch: 614 | Loss: 0.00794693863014752 | Accuracy: 1.0 Epoch: 615 | Loss: 0.007934238293627341 | Accuracy: 1.0 Epoch: 616 | Loss: 0.007921578640580539 | Accuracy: 1.0 Epoch: 617 | Loss: 0.00790895947530772 | Accuracy: 1.0 Epoch: 618 | Loss: 0.007896380603365527 | Accuracy: 1.0 Epoch: 619 | Loss: 0.007883841831556153 | Accuracy: 1.0 Epoch: 620 | Loss: 0.00787134296791811 | Accuracy: 1.0 Epoch: 621 | Loss: 0.007858883821715073 | Accuracy: 1.0 Epoch: 622 | Loss: 0.007846464203427394 | Accuracy: 1.0 Epoch: 623 | Loss: 0.007834083924741502 | Accuracy: 1.0 Epoch: 624 | Loss: 0.007821742798540976 | Accuracy: 1.0 Epoch: 625 | Loss: 0.007809440638896529 | Accuracy: 1.0 Epoch: 626 | Loss: 0.007797177261056631 | Accuracy: 1.0 Epoch: 627 | Loss: 0.007784952481438632 | Accuracy: 1.0 Epoch: 628 | Loss: 0.0077727661176188855 | Accuracy: 1.0 Epoch: 629 | Loss: 0.007760617988324093 | Accuracy: 1.0 Epoch: 630 | Loss: 0.0077485079134220715 | Accuracy: 1.0 Epoch: 631 | Loss: 0.007736435713912565 | Accuracy: 1.0 Epoch: 632 | Loss: 0.007724401211918841 | Accuracy: 1.0 Epoch: 633 | Loss: 0.00771240423067841 | Accuracy: 1.0 Epoch: 634 | Loss: 0.007700444594534521 | Accuracy: 1.0 Epoch: 635 | Loss: 0.007688522128927224 | Accuracy: 1.0 Epoch: 636 | Loss: 0.007676636660385395 | Accuracy: 1.0 Epoch: 637 | Loss: 0.0076647880165177425 | Accuracy: 1.0 Epoch: 638 | Loss: 0.007652976026004494 | Accuracy: 1.0 Epoch: 639 | Loss: 0.007641200518589284 | Accuracy: 1.0 Epoch: 640 | Loss: 0.007629461325070553 | Accuracy: 1.0 Epoch: 641 | Loss: 0.007617758277293657 | Accuracy: 1.0 Epoch: 642 | Loss: 0.007606091208142862 | Accuracy: 1.0 Epoch: 643 | Loss: 0.007594459951532809 | Accuracy: 1.0 Epoch: 644 | Loss: 0.007582864342401139 | Accuracy: 1.0 Epoch: 645 | Loss: 0.007571304216700315 | Accuracy: 1.0 Epoch: 646 | Loss: 0.007559779411389677 | Accuracy: 1.0 Epoch: 647 | Loss: 0.0075482897644285115 | Accuracy: 1.0 Epoch: 648 | Loss: 0.007536835114767147 | Accuracy: 1.0 Epoch: 649 | Loss: 0.007525415302340403 | Accuracy: 1.0 Epoch: 650 | Loss: 0.00751403016805947 | Accuracy: 1.0 Epoch: 651 | Loss: 0.007502679553804759 | Accuracy: 1.0 Epoch: 652 | Loss: 0.0074913633024187316 | Accuracy: 1.0 Epoch: 653 | Loss: 0.007480081257697828 | Accuracy: 1.0 Epoch: 654 | Loss: 0.00746883326438592 | Accuracy: 1.0 Epoch: 655 | Loss: 0.00745761916816688 | Accuracy: 1.0 Epoch: 656 | Loss: 0.007446438815657616 | Accuracy: 1.0 Epoch: 657 | Loss: 0.007435292054400609 | Accuracy: 1.0 Epoch: 658 | Loss: 0.007424178732857362 | Accuracy: 1.0 Epoch: 659 | Loss: 0.007413098700401362 | Accuracy: 1.0 Epoch: 660 | Loss: 0.007402051807311177 | Accuracy: 1.0 Epoch: 661 | Loss: 0.00739103790476348 | Accuracy: 1.0 Epoch: 662 | Loss: 0.00738005684482672 | Accuracy: 1.0 Epoch: 663 | Loss: 0.007369108480453982 | Accuracy: 1.0 Epoch: 664 | Loss: 0.007358192665476914 | Accuracy: 1.0 Epoch: 665 | Loss: 0.007347309254598564 | Accuracy: 1.0 Epoch: 666 | Loss: 0.0073364581033872455 | Accuracy: 1.0 Epoch: 667 | Loss: 0.007325639068270195 | Accuracy: 1.0 Epoch: 668 | Loss: 0.0073148520065267775 | Accuracy: 1.0 Epoch: 669 | Loss: 0.007304096776282463 | Accuracy: 1.0 Epoch: 670 | Loss: 0.007293373236502635 | Accuracy: 1.0 Epoch: 671 | Loss: 0.007282681246986045 | Accuracy: 1.0 Epoch: 672 | Loss: 0.007272020668358985 | Accuracy: 1.0 Epoch: 673 | Loss: 0.00726139136206902 | Accuracy: 1.0 Epoch: 674 | Loss: 0.007250793190378945 | Accuracy: 1.0 Epoch: 675 | Loss: 0.0072402260163604995 | Accuracy: 1.0 Epoch: 676 | Loss: 0.0072296897038894 | Accuracy: 1.0 Epoch: 677 | Loss: 0.007219184117638119 | Accuracy: 1.0 Epoch: 678 | Loss: 0.007208709123071052 | Accuracy: 1.0 Epoch: 679 | Loss: 0.0071982645864383235 | Accuracy: 1.0 Epoch: 680 | Loss: 0.007187850374769966 | Accuracy: 1.0 Epoch: 681 | Loss: 0.007177466355870573 | Accuracy: 1.0 Epoch: 682 | Loss: 0.007167112398313217 | Accuracy: 1.0 Epoch: 683 | Loss: 0.0071567883714343476 | Accuracy: 1.0 Epoch: 684 | Loss: 0.007146494145327876 | Accuracy: 1.0 Epoch: 685 | Loss: 0.007136229590839794 | Accuracy: 1.0 Epoch: 686 | Loss: 0.0071259945795627624 | Accuracy: 1.0 Epoch: 687 | Loss: 0.007115788983830697 | Accuracy: 1.0 Epoch: 688 | Loss: 0.007105612676713623 | Accuracy: 1.0 Epoch: 689 | Loss: 0.007095465532011773 | Accuracy: 1.0 Epoch: 690 | Loss: 0.007085347424251171 | Accuracy: 1.0 Epoch: 691 | Loss: 0.007075258228677481 | Accuracy: 1.0 Epoch: 692 | Loss: 0.0070651978212518405 | Accuracy: 1.0 Epoch: 693 | Loss: 0.007055166078644945 | Accuracy: 1.0 Epoch: 694 | Loss: 0.007045162878232212 | Accuracy: 1.0 Epoch: 695 | Loss: 0.00703518809808916 | Accuracy: 1.0 Epoch: 696 | Loss: 0.007025241616985599 | Accuracy: 1.0 Epoch: 697 | Loss: 0.0070153233143812116 | Accuracy: 1.0 Epoch: 698 | Loss: 0.007005433070420945 | Accuracy: 1.0 Epoch: 699 | Loss: 0.006995570765929358 | Accuracy: 1.0 Epoch: 700 | Loss: 0.006985736282406358 | Accuracy: 1.0
plot_colored_graph(model, X, y)
<ipython-input-13-ff87a8808486>:9: MatplotlibDeprecationWarning: shading='flat' when X and Y have the same dimensions as C is deprecated since 3.3. Either specify the corners of the quadrilaterals with X and Y, or pass shading='auto', 'nearest' or 'gouraud', or set rcParams['pcolor.shading']. This will become an error two minor releases later. plt.pcolormesh(xx, yy, Z, cmap=cmap_light)
X, y = np.array([[1, 0], [1, 1], [0, 1], [0, 0]]), np.array([1, 0, 1, 0])
plot_graph(X, y)
model = Sequential(
Linear(2, 8),
ReLU(),
Linear(8, 2),
)
optimizer = SGD(model.parameters(), lr=5e-2, momentum=0.9)
criterion = CrossEntropyLoss()
train_model(X, y, model, optimizer, criterion, 700)
4126 | Accuracy: 1.0 Epoch: 349 | Loss: 0.002459844305706624 | Accuracy: 1.0 Epoch: 350 | Loss: 0.0024494757777481523 | Accuracy: 1.0 Epoch: 351 | Loss: 0.002439335453284056 | Accuracy: 1.0 Epoch: 352 | Loss: 0.002429899658711762 | Accuracy: 1.0 Epoch: 353 | Loss: 0.0024202584670458627 | Accuracy: 1.0 Epoch: 354 | Loss: 0.0024106092214497997 | Accuracy: 1.0 Epoch: 355 | Loss: 0.0024008599220094315 | Accuracy: 1.0 Epoch: 356 | Loss: 0.002391263616551339 | Accuracy: 1.0 Epoch: 357 | Loss: 0.002381756885779605 | Accuracy: 1.0 Epoch: 358 | Loss: 0.00237248652071142 | Accuracy: 1.0 Epoch: 359 | Loss: 0.0023630590335737287 | Accuracy: 1.0 Epoch: 360 | Loss: 0.0023535877802887393 | Accuracy: 1.0 Epoch: 361 | Loss: 0.0023446228121030838 | Accuracy: 1.0 Epoch: 362 | Loss: 0.0023357959586420675 | Accuracy: 1.0 Epoch: 363 | Loss: 0.0023267894841640354 | Accuracy: 1.0 Epoch: 364 | Loss: 0.0023179695198524775 | Accuracy: 1.0 Epoch: 365 | Loss: 0.0023087366007241055 | Accuracy: 1.0 Epoch: 366 | Loss: 0.0022999607073421343 | Accuracy: 1.0 Epoch: 367 | Loss: 0.002291190170063636 | Accuracy: 1.0 Epoch: 368 | Loss: 0.002281905445573084 | Accuracy: 1.0 Epoch: 369 | Loss: 0.0022733314647748575 | Accuracy: 1.0 Epoch: 370 | Loss: 0.002264827905776463 | Accuracy: 1.0 Epoch: 371 | Loss: 0.002256309397518607 | Accuracy: 1.0 Epoch: 372 | Loss: 0.0022481936783868258 | Accuracy: 1.0 Epoch: 373 | Loss: 0.002239493897626254 | Accuracy: 1.0 Epoch: 374 | Loss: 0.002231332787265169 | Accuracy: 1.0 Epoch: 375 | Loss: 0.0022232192826007005 | Accuracy: 1.0 Epoch: 376 | Loss: 0.0022147707435237066 | Accuracy: 1.0 Epoch: 377 | Loss: 0.0022062941697669138 | Accuracy: 1.0 Epoch: 378 | Loss: 0.00219823392309503 | Accuracy: 1.0 Epoch: 379 | Loss: 0.0021900692593754788 | Accuracy: 1.0 Epoch: 380 | Loss: 0.00218195239142961 | Accuracy: 1.0 Epoch: 381 | Loss: 0.002174060927541877 | Accuracy: 1.0 Epoch: 382 | Loss: 0.0021658428976452627 | Accuracy: 1.0 Epoch: 383 | Loss: 0.0021579874526542918 | Accuracy: 1.0 Epoch: 384 | Loss: 0.0021502572348552802 | Accuracy: 1.0 Epoch: 385 | Loss: 0.0021425404267350822 | Accuracy: 1.0 Epoch: 386 | Loss: 0.0021348453629351457 | Accuracy: 1.0 Epoch: 387 | Loss: 0.0021269524940872447 | Accuracy: 1.0 Epoch: 388 | Loss: 0.002119542198075256 | Accuracy: 1.0 Epoch: 389 | Loss: 0.002112075407768547 | Accuracy: 1.0 Epoch: 390 | Loss: 0.0021043442541856627 | Accuracy: 1.0 Epoch: 391 | Loss: 0.0020971604590953223 | Accuracy: 1.0 Epoch: 392 | Loss: 0.0020896266507338893 | Accuracy: 1.0 Epoch: 393 | Loss: 0.002082421992269707 | Accuracy: 1.0 Epoch: 394 | Loss: 0.002075498816128148 | Accuracy: 1.0 Epoch: 395 | Loss: 0.0020681180253796314 | Accuracy: 1.0 Epoch: 396 | Loss: 0.0020622344302906803 | Accuracy: 1.0 Epoch: 397 | Loss: 0.0020563276412736186 | Accuracy: 1.0 Epoch: 398 | Loss: 0.0020505892608200264 | Accuracy: 1.0 Epoch: 399 | Loss: 0.0020447186248516384 | Accuracy: 1.0 Epoch: 400 | Loss: 0.00203839816195018 | Accuracy: 1.0 Epoch: 401 | Loss: 0.002032437213622811 | Accuracy: 1.0 Epoch: 402 | Loss: 0.0020264580238782515 | Accuracy: 1.0 Epoch: 403 | Loss: 0.002020272246141948 | Accuracy: 1.0 Epoch: 404 | Loss: 0.0020139813746489965 | Accuracy: 1.0 Epoch: 405 | Loss: 0.00200817894111724 | Accuracy: 1.0 Epoch: 406 | Loss: 0.002002097872923117 | Accuracy: 1.0 Epoch: 407 | Loss: 0.001995714025327563 | Accuracy: 1.0 Epoch: 408 | Loss: 0.001989633224966816 | Accuracy: 1.0 Epoch: 409 | Loss: 0.0019837654011039493 | Accuracy: 1.0 Epoch: 410 | Loss: 0.0019777189296335614 | Accuracy: 1.0 Epoch: 411 | Loss: 0.0019721119801031266 | Accuracy: 1.0 Epoch: 412 | Loss: 0.0019667671274737598 | Accuracy: 1.0 Epoch: 413 | Loss: 0.0019613564423537166 | Accuracy: 1.0 Epoch: 414 | Loss: 0.0019559056637786423 | Accuracy: 1.0 Epoch: 415 | Loss: 0.0019500542226896197 | Accuracy: 1.0 Epoch: 416 | Loss: 0.001944793074169194 | Accuracy: 1.0 Epoch: 417 | Loss: 0.0019393091510531472 | Accuracy: 1.0 Epoch: 418 | Loss: 0.0019331423959877314 | Accuracy: 1.0 Epoch: 419 | Loss: 0.0019276052791140216 | Accuracy: 1.0 Epoch: 420 | Loss: 0.0019225240969101493 | Accuracy: 1.0 Epoch: 421 | Loss: 0.001917223274382521 | Accuracy: 1.0 Epoch: 422 | Loss: 0.0019121813803047606 | Accuracy: 1.0 Epoch: 423 | Loss: 0.0019067434581521254 | Accuracy: 1.0 Epoch: 424 | Loss: 0.0019017743061547892 | Accuracy: 1.0 Epoch: 425 | Loss: 0.0018964358562252451 | Accuracy: 1.0 Epoch: 426 | Loss: 0.0018911182525461275 | Accuracy: 1.0 Epoch: 427 | Loss: 0.0018858897056900712 | Accuracy: 1.0 Epoch: 428 | Loss: 0.0018810206380376233 | Accuracy: 1.0 Epoch: 429 | Loss: 0.0018762264147734009 | Accuracy: 1.0 Epoch: 430 | Loss: 0.0018713195808845017 | Accuracy: 1.0 Epoch: 431 | Loss: 0.0018662943733077767 | Accuracy: 1.0 Epoch: 432 | Loss: 0.0018611279325819112 | Accuracy: 1.0 Epoch: 433 | Loss: 0.0018561179754007632 | Accuracy: 1.0 Epoch: 434 | Loss: 0.0018512660197146837 | Accuracy: 1.0 Epoch: 435 | Loss: 0.0018468336264036661 | Accuracy: 1.0 Epoch: 436 | Loss: 0.001842140092739502 | Accuracy: 1.0 Epoch: 437 | Loss: 0.001837181816452582 | Accuracy: 1.0 Epoch: 438 | Loss: 0.0018320124437661719 | Accuracy: 1.0 Epoch: 439 | Loss: 0.0018277043343606731 | Accuracy: 1.0 Epoch: 440 | Loss: 0.0018229527670317394 | Accuracy: 1.0 Epoch: 441 | Loss: 0.0018179884670243402 | Accuracy: 1.0 Epoch: 442 | Loss: 0.001813676567812318 | Accuracy: 1.0 Epoch: 443 | Loss: 0.0018090705753402267 | Accuracy: 1.0 Epoch: 444 | Loss: 0.0018044239965306842 | Accuracy: 1.0 Epoch: 445 | Loss: 0.0017995465509553115 | Accuracy: 1.0 Epoch: 446 | Loss: 0.0017949238894943297 | Accuracy: 1.0 Epoch: 447 | Loss: 0.0017908739648409208 | Accuracy: 1.0 Epoch: 448 | Loss: 0.0017863121486820805 | Accuracy: 1.0 Epoch: 449 | Loss: 0.0017813266257113375 | Accuracy: 1.0 Epoch: 450 | Loss: 0.0017771308468927508 | Accuracy: 1.0 Epoch: 451 | Loss: 0.0017726825378909345 | Accuracy: 1.0 Epoch: 452 | Loss: 0.0017685418464746334 | Accuracy: 1.0 Epoch: 453 | Loss: 0.0017641487026136826 | Accuracy: 1.0 Epoch: 454 | Loss: 0.0017595313951864538 | Accuracy: 1.0 Epoch: 455 | Loss: 0.0017553309736508687 | Accuracy: 1.0 Epoch: 456 | Loss: 0.0017507856543621638 | Accuracy: 1.0 Epoch: 457 | Loss: 0.001746359433234329 | Accuracy: 1.0 Epoch: 458 | Loss: 0.0017422751875151039 | Accuracy: 1.0 Epoch: 459 | Loss: 0.0017380805317131762 | Accuracy: 1.0 Epoch: 460 | Loss: 0.001733919804477407 | Accuracy: 1.0 Epoch: 461 | Loss: 0.0017296162010743015 | Accuracy: 1.0 Epoch: 462 | Loss: 0.0017254477150601614 | Accuracy: 1.0 Epoch: 463 | Loss: 0.0017211052976038106 | Accuracy: 1.0 Epoch: 464 | Loss: 0.0017175026343896594 | Accuracy: 1.0 Epoch: 465 | Loss: 0.0017134991045057988 | Accuracy: 1.0 Epoch: 466 | Loss: 0.0017091336698872692 | Accuracy: 1.0 Epoch: 467 | Loss: 0.0017049694233807959 | Accuracy: 1.0 Epoch: 468 | Loss: 0.0017011258292919107 | Accuracy: 1.0 Epoch: 469 | Loss: 0.0016970582427229344 | Accuracy: 1.0 Epoch: 470 | Loss: 0.0016929141449519836 | Accuracy: 1.0 Epoch: 471 | Loss: 0.0016889955871864188 | Accuracy: 1.0 Epoch: 472 | Loss: 0.0016852053515333796 | Accuracy: 1.0 Epoch: 473 | Loss: 0.0016812804153104478 | Accuracy: 1.0 Epoch: 474 | Loss: 0.0016768712856223 | Accuracy: 1.0 Epoch: 475 | Loss: 0.001673466645706191 | Accuracy: 1.0 Epoch: 476 | Loss: 0.0016699155153518772 | Accuracy: 1.0 Epoch: 477 | Loss: 0.0016660757802505395 | Accuracy: 1.0 Epoch: 478 | Loss: 0.001661962883647814 | Accuracy: 1.0 Epoch: 479 | Loss: 0.001658030967178572 | Accuracy: 1.0 Epoch: 480 | Loss: 0.00165433736883796 | Accuracy: 1.0 Epoch: 481 | Loss: 0.0016505211906241712 | Accuracy: 1.0 Epoch: 482 | Loss: 0.0016468284993881419 | Accuracy: 1.0 Epoch: 483 | Loss: 0.0016428601509262252 | Accuracy: 1.0 Epoch: 484 | Loss: 0.0016388487731778126 | Accuracy: 1.0 Epoch: 485 | Loss: 0.0016350079775729574 | Accuracy: 1.0 Epoch: 486 | Loss: 0.0016315745751633104 | Accuracy: 1.0 Epoch: 487 | Loss: 0.0016279580215263418 | Accuracy: 1.0 Epoch: 488 | Loss: 0.0016243067840706195 | Accuracy: 1.0 Epoch: 489 | Loss: 0.001620651478500535 | Accuracy: 1.0 Epoch: 490 | Loss: 0.001616849099138339 | Accuracy: 1.0 Epoch: 491 | Loss: 0.0016129085568289151 | Accuracy: 1.0 Epoch: 492 | Loss: 0.0016092219740705105 | Accuracy: 1.0 Epoch: 493 | Loss: 0.0016058266805987686 | Accuracy: 1.0 Epoch: 494 | Loss: 0.0016022972805811572 | Accuracy: 1.0 Epoch: 495 | Loss: 0.0015987795192991927 | Accuracy: 1.0 Epoch: 496 | Loss: 0.0015952067129353072 | Accuracy: 1.0 Epoch: 497 | Loss: 0.0015915843141037175 | Accuracy: 1.0 Epoch: 498 | Loss: 0.0015882362002540152 | Accuracy: 1.0 Epoch: 499 | Loss: 0.0015844479069835368 | Accuracy: 1.0 Epoch: 500 | Loss: 0.0015810364687954053 | Accuracy: 1.0 Epoch: 501 | Loss: 0.0015777957332038302 | Accuracy: 1.0 Epoch: 502 | Loss: 0.0015742904014616967 | Accuracy: 1.0 Epoch: 503 | Loss: 0.0015706074962900125 | Accuracy: 1.0 Epoch: 504 | Loss: 0.001567204478936872 | Accuracy: 1.0 Epoch: 505 | Loss: 0.001563587691653586 | Accuracy: 1.0 Epoch: 506 | Loss: 0.0015603745358784911 | Accuracy: 1.0 Epoch: 507 | Loss: 0.0015571777172674749 | Accuracy: 1.0 Epoch: 508 | Loss: 0.0015537962414152102 | Accuracy: 1.0 Epoch: 509 | Loss: 0.0015504121963165114 | Accuracy: 1.0 Epoch: 510 | Loss: 0.0015469572100247756 | Accuracy: 1.0 Epoch: 511 | Loss: 0.0015435204579343953 | Accuracy: 1.0 Epoch: 512 | Loss: 0.0015403987388578314 | Accuracy: 1.0 Epoch: 513 | Loss: 0.0015371591063186017 | Accuracy: 1.0 Epoch: 514 | Loss: 0.0015338318864144074 | Accuracy: 1.0 Epoch: 515 | Loss: 0.0015306547643229732 | Accuracy: 1.0 Epoch: 516 | Loss: 0.001527329183731821 | Accuracy: 1.0 Epoch: 517 | Loss: 0.001523971960509199 | Accuracy: 1.0 Epoch: 518 | Loss: 0.0015210309791408845 | Accuracy: 1.0 Epoch: 519 | Loss: 0.0015178138716795335 | Accuracy: 1.0 Epoch: 520 | Loss: 0.001514593405088598 | Accuracy: 1.0 Epoch: 521 | Loss: 0.001511384942552779 | Accuracy: 1.0 Epoch: 522 | Loss: 0.001508340872485972 | Accuracy: 1.0 Epoch: 523 | Loss: 0.0015051341584125088 | Accuracy: 1.0 Epoch: 524 | Loss: 0.0015019498852465194 | Accuracy: 1.0 Epoch: 525 | Loss: 0.0014990213182459766 | Accuracy: 1.0 Epoch: 526 | Loss: 0.001495781642614691 | Accuracy: 1.0 Epoch: 527 | Loss: 0.0014926929705304129 | Accuracy: 1.0 Epoch: 528 | Loss: 0.0014896503973798095 | Accuracy: 1.0 Epoch: 529 | Loss: 0.001486397069864384 | Accuracy: 1.0 Epoch: 530 | Loss: 0.0014835347667800547 | Accuracy: 1.0 Epoch: 531 | Loss: 0.0014804897423190471 | Accuracy: 1.0 Epoch: 532 | Loss: 0.00147734864482272 | Accuracy: 1.0 Epoch: 533 | Loss: 0.0014741905008245953 | Accuracy: 1.0 Epoch: 534 | Loss: 0.0014713364363106844 | Accuracy: 1.0 Epoch: 535 | Loss: 0.0014681425383608203 | Accuracy: 1.0 Epoch: 536 | Loss: 0.0014652007824377498 | Accuracy: 1.0 Epoch: 537 | Loss: 0.0014622975161971215 | Accuracy: 1.0 Epoch: 538 | Loss: 0.0014592857522512746 | Accuracy: 1.0 Epoch: 539 | Loss: 0.0014564038412508314 | Accuracy: 1.0 Epoch: 540 | Loss: 0.0014534482985372325 | Accuracy: 1.0 Epoch: 541 | Loss: 0.001450412330856528 | Accuracy: 1.0 Epoch: 542 | Loss: 0.001447603526678641 | Accuracy: 1.0 Epoch: 543 | Loss: 0.0014447827255130437 | Accuracy: 1.0 Epoch: 544 | Loss: 0.0014417459931291726 | Accuracy: 1.0 Epoch: 545 | Loss: 0.0014387762431111314 | Accuracy: 1.0 Epoch: 546 | Loss: 0.0014362416997660357 | Accuracy: 1.0 Epoch: 547 | Loss: 0.0014333779651646032 | Accuracy: 1.0 Epoch: 548 | Loss: 0.0014305376819022469 | Accuracy: 1.0 Epoch: 549 | Loss: 0.0014277476711408884 | Accuracy: 1.0 Epoch: 550 | Loss: 0.0014247669054701217 | Accuracy: 1.0 Epoch: 551 | Loss: 0.0014218158819034308 | Accuracy: 1.0 Epoch: 552 | Loss: 0.0014192242824240006 | Accuracy: 1.0 Epoch: 553 | Loss: 0.0014165679903549023 | Accuracy: 1.0 Epoch: 554 | Loss: 0.0014136731302633564 | Accuracy: 1.0 Epoch: 555 | Loss: 0.0014108922712168684 | Accuracy: 1.0 Epoch: 556 | Loss: 0.0014081673064720206 | Accuracy: 1.0 Epoch: 557 | Loss: 0.0014054941119854177 | Accuracy: 1.0 Epoch: 558 | Loss: 0.0014026948367113423 | Accuracy: 1.0 Epoch: 559 | Loss: 0.0014000301103884033 | Accuracy: 1.0 Epoch: 560 | Loss: 0.0013972336949806914 | Accuracy: 1.0 Epoch: 561 | Loss: 0.0013943714346782432 | Accuracy: 1.0 Epoch: 562 | Loss: 0.0013919823656585572 | Accuracy: 1.0 Epoch: 563 | Loss: 0.0013893512092556636 | Accuracy: 1.0 Epoch: 564 | Loss: 0.0013866734021224527 | Accuracy: 1.0 Epoch: 565 | Loss: 0.0013839662831185624 | Accuracy: 1.0 Epoch: 566 | Loss: 0.0013812873388842485 | Accuracy: 1.0 Epoch: 567 | Loss: 0.0013786487886785252 | Accuracy: 1.0 Epoch: 568 | Loss: 0.0013758907558269456 | Accuracy: 1.0 Epoch: 569 | Loss: 0.0013734319117991891 | Accuracy: 1.0 Epoch: 570 | Loss: 0.001370898484687113 | Accuracy: 1.0 Epoch: 571 | Loss: 0.0013681911636096004 | Accuracy: 1.0 Epoch: 572 | Loss: 0.0013653160362066107 | Accuracy: 1.0 Epoch: 573 | Loss: 0.0013631438814417334 | Accuracy: 1.0 Epoch: 574 | Loss: 0.0013608337528522964 | Accuracy: 1.0 Epoch: 575 | Loss: 0.001358125313381817 | Accuracy: 1.0 Epoch: 576 | Loss: 0.0013551285329547983 | Accuracy: 1.0 Epoch: 577 | Loss: 0.0013529292594882266 | Accuracy: 1.0 Epoch: 578 | Loss: 0.0013507769456169304 | Accuracy: 1.0 Epoch: 579 | Loss: 0.0013482688145630803 | Accuracy: 1.0 Epoch: 580 | Loss: 0.0013454794931908494 | Accuracy: 1.0 Epoch: 581 | Loss: 0.001342850147433031 | Accuracy: 1.0 Epoch: 582 | Loss: 0.0013404104633944545 | Accuracy: 1.0 Epoch: 583 | Loss: 0.0013378534605494024 | Accuracy: 1.0 Epoch: 584 | Loss: 0.0013357068142856678 | Accuracy: 1.0 Epoch: 585 | Loss: 0.0013333114712869016 | Accuracy: 1.0 Epoch: 586 | Loss: 0.0013305692119194251 | Accuracy: 1.0 Epoch: 587 | Loss: 0.0013277492345913325 | Accuracy: 1.0 Epoch: 588 | Loss: 0.0013254599087788247 | Accuracy: 1.0 Epoch: 589 | Loss: 0.001323197999435114 | Accuracy: 1.0 Epoch: 590 | Loss: 0.001320711453578479 | Accuracy: 1.0 Epoch: 591 | Loss: 0.0013179469870200457 | Accuracy: 1.0 Epoch: 592 | Loss: 0.0013159857584489672 | Accuracy: 1.0 Epoch: 593 | Loss: 0.0013138128495141996 | Accuracy: 1.0 Epoch: 594 | Loss: 0.0013113332773294914 | Accuracy: 1.0 Epoch: 595 | Loss: 0.001308560799230315 | Accuracy: 1.0 Epoch: 596 | Loss: 0.0013063699889499692 | Accuracy: 1.0 Epoch: 597 | Loss: 0.001304259558332224 | Accuracy: 1.0 Epoch: 598 | Loss: 0.001301892728964359 | Accuracy: 1.0 Epoch: 599 | Loss: 0.0012994198653762347 | Accuracy: 1.0 Epoch: 600 | Loss: 0.0012968705490477527 | Accuracy: 1.0 Epoch: 601 | Loss: 0.0012944135568361387 | Accuracy: 1.0 Epoch: 602 | Loss: 0.0012923058246798822 | Accuracy: 1.0 Epoch: 603 | Loss: 0.0012901181612824978 | Accuracy: 1.0 Epoch: 604 | Loss: 0.001287602993264779 | Accuracy: 1.0 Epoch: 605 | Loss: 0.0012853038476158237 | Accuracy: 1.0 Epoch: 606 | Loss: 0.0012831602087193406 | Accuracy: 1.0 Epoch: 607 | Loss: 0.001280894387367905 | Accuracy: 1.0 Epoch: 608 | Loss: 0.0012784711528670114 | Accuracy: 1.0 Epoch: 609 | Loss: 0.0012759730573988323 | Accuracy: 1.0 Epoch: 610 | Loss: 0.0012737324518378747 | Accuracy: 1.0 Epoch: 611 | Loss: 0.0012714860688722161 | Accuracy: 1.0 Epoch: 612 | Loss: 0.0012691239580440881 | Accuracy: 1.0 Epoch: 613 | Loss: 0.0012669775332493699 | Accuracy: 1.0 Epoch: 614 | Loss: 0.0012646711900991528 | Accuracy: 1.0 Epoch: 615 | Loss: 0.0012626361030502267 | Accuracy: 1.0 Epoch: 616 | Loss: 0.0012603926183001116 | Accuracy: 1.0 Epoch: 617 | Loss: 0.0012580466559197257 | Accuracy: 1.0 Epoch: 618 | Loss: 0.0012558878180216942 | Accuracy: 1.0 Epoch: 619 | Loss: 0.0012537569797943066 | Accuracy: 1.0 Epoch: 620 | Loss: 0.0012514777827380248 | Accuracy: 1.0 Epoch: 621 | Loss: 0.0012492718854058243 | Accuracy: 1.0 Epoch: 622 | Loss: 0.0012471321983588191 | Accuracy: 1.0 Epoch: 623 | Loss: 0.0012451357551487737 | Accuracy: 1.0 Epoch: 624 | Loss: 0.0012429593382410422 | Accuracy: 1.0 Epoch: 625 | Loss: 0.0012407169470104488 | Accuracy: 1.0 Epoch: 626 | Loss: 0.00123864199929294 | Accuracy: 1.0 Epoch: 627 | Loss: 0.0012364988514887779 | Accuracy: 1.0 Epoch: 628 | Loss: 0.0012345761238178104 | Accuracy: 1.0 Epoch: 629 | Loss: 0.001232446733128333 | Accuracy: 1.0 Epoch: 630 | Loss: 0.0012303603115895827 | Accuracy: 1.0 Epoch: 631 | Loss: 0.0012282818898090213 | Accuracy: 1.0 Epoch: 632 | Loss: 0.0012259963272902418 | Accuracy: 1.0 Epoch: 633 | Loss: 0.0012238569203180632 | Accuracy: 1.0 Epoch: 634 | Loss: 0.0012218396981222926 | Accuracy: 1.0 Epoch: 635 | Loss: 0.0012197522173536945 | Accuracy: 1.0 Epoch: 636 | Loss: 0.0012176021391171578 | Accuracy: 1.0 Epoch: 637 | Loss: 0.0012156455633375552 | Accuracy: 1.0 Epoch: 638 | Loss: 0.0012135534392060453 | Accuracy: 1.0 Epoch: 639 | Loss: 0.0012115934364525386 | Accuracy: 1.0 Epoch: 640 | Loss: 0.0012096437506794989 | Accuracy: 1.0 Epoch: 641 | Loss: 0.0012074125664781154 | Accuracy: 1.0 Epoch: 642 | Loss: 0.0012056057162017433 | Accuracy: 1.0 Epoch: 643 | Loss: 0.0012036485088463907 | Accuracy: 1.0 Epoch: 644 | Loss: 0.0012015310227064249 | Accuracy: 1.0 Epoch: 645 | Loss: 0.0011994024601470607 | Accuracy: 1.0 Epoch: 646 | Loss: 0.0011973517769922949 | Accuracy: 1.0 Epoch: 647 | Loss: 0.0011953988381540662 | Accuracy: 1.0 Epoch: 648 | Loss: 0.0011935085780243907 | Accuracy: 1.0 Epoch: 649 | Loss: 0.001191352989111833 | Accuracy: 1.0 Epoch: 650 | Loss: 0.0011893772112550939 | Accuracy: 1.0 Epoch: 651 | Loss: 0.0011874434672149586 | Accuracy: 1.0 Epoch: 652 | Loss: 0.0011853447511405843 | Accuracy: 1.0 Epoch: 653 | Loss: 0.00118362928004356 | Accuracy: 1.0 Epoch: 654 | Loss: 0.0011817757911703067 | Accuracy: 1.0 Epoch: 655 | Loss: 0.0011797665584065327 | Accuracy: 1.0 Epoch: 656 | Loss: 0.001177740760294383 | Accuracy: 1.0 Epoch: 657 | Loss: 0.0011758108217855242 | Accuracy: 1.0 Epoch: 658 | Loss: 0.0011738470842316113 | Accuracy: 1.0 Epoch: 659 | Loss: 0.0011720878559747369 | Accuracy: 1.0 Epoch: 660 | Loss: 0.0011701418027933578 | Accuracy: 1.0 Epoch: 661 | Loss: 0.0011681492330223885 | Accuracy: 1.0 Epoch: 662 | Loss: 0.0011662654317112274 | Accuracy: 1.0 Epoch: 663 | Loss: 0.001164350665165979 | Accuracy: 1.0 Epoch: 664 | Loss: 0.0011623977427984407 | Accuracy: 1.0 Epoch: 665 | Loss: 0.0011604566727700942 | Accuracy: 1.0 Epoch: 666 | Loss: 0.001158581246667168 | Accuracy: 1.0 Epoch: 667 | Loss: 0.0011566752935668965 | Accuracy: 1.0 Epoch: 668 | Loss: 0.0011549507050279176 | Accuracy: 1.0 Epoch: 669 | Loss: 0.0011531054044334142 | Accuracy: 1.0 Epoch: 670 | Loss: 0.0011511198198561484 | Accuracy: 1.0 Epoch: 671 | Loss: 0.0011491867898675465 | Accuracy: 1.0 Epoch: 672 | Loss: 0.0011474017177856787 | Accuracy: 1.0 Epoch: 673 | Loss: 0.0011456445220028254 | Accuracy: 1.0 Epoch: 674 | Loss: 0.0011437800893174003 | Accuracy: 1.0 Epoch: 675 | Loss: 0.0011419375579950599 | Accuracy: 1.0 Epoch: 676 | Loss: 0.0011402684757295684 | Accuracy: 1.0 Epoch: 677 | Loss: 0.001138417808440714 | Accuracy: 1.0 Epoch: 678 | Loss: 0.001136473576389464 | Accuracy: 1.0 Epoch: 679 | Loss: 0.0011348786649728302 | Accuracy: 1.0 Epoch: 680 | Loss: 0.0011330745354542018 | Accuracy: 1.0 Epoch: 681 | Loss: 0.0011310844371788028 | Accuracy: 1.0 Epoch: 682 | Loss: 0.0011293000677807107 | Accuracy: 1.0 Epoch: 683 | Loss: 0.0011275048697066416 | Accuracy: 1.0 Epoch: 684 | Loss: 0.0011258894550798468 | Accuracy: 1.0 Epoch: 685 | Loss: 0.0011240798676618669 | Accuracy: 1.0 Epoch: 686 | Loss: 0.001122282793202607 | Accuracy: 1.0 Epoch: 687 | Loss: 0.0011204434585861795 | Accuracy: 1.0 Epoch: 688 | Loss: 0.0011186804962323353 | Accuracy: 1.0 Epoch: 689 | Loss: 0.0011170081328741336 | Accuracy: 1.0 Epoch: 690 | Loss: 0.0011152467887226055 | Accuracy: 1.0 Epoch: 691 | Loss: 0.0011135676109544853 | Accuracy: 1.0 Epoch: 692 | Loss: 0.0011117707527096208 | Accuracy: 1.0 Epoch: 693 | Loss: 0.0011099863756541728 | Accuracy: 1.0 Epoch: 694 | Loss: 0.001108334523029392 | Accuracy: 1.0 Epoch: 695 | Loss: 0.0011066018748964478 | Accuracy: 1.0 Epoch: 696 | Loss: 0.001104971737936441 | Accuracy: 1.0 Epoch: 697 | Loss: 0.0011032487449970573 | Accuracy: 1.0 Epoch: 698 | Loss: 0.0011014832794826364 | Accuracy: 1.0 Epoch: 699 | Loss: 0.0010997844783950186 | Accuracy: 1.0 Epoch: 700 | Loss: 0.0010981688139428496 | Accuracy: 1.0
plot_colored_graph(model, X, y)
<ipython-input-13-ff87a8808486>:9: MatplotlibDeprecationWarning: shading='flat' when X and Y have the same dimensions as C is deprecated since 3.3. Either specify the corners of the quadrilaterals with X and Y, or pass shading='auto', 'nearest' or 'gouraud', or set rcParams['pcolor.shading']. This will become an error two minor releases later. plt.pcolormesh(xx, yy, Z, cmap=cmap_light)
model = Sequential(
Linear(2, 8),
Sigmoid(),
Linear(8, 2),
)
optimizer = SGD(model.parameters(), lr=3e-2, momentum=0.9)
criterion = CrossEntropyLoss()
train_model(X, y, model, optimizer, criterion, 2000)
34489999 | Accuracy: 1.0 Epoch: 1650 | Loss: 0.009245954987302678 | Accuracy: 1.0 Epoch: 1651 | Loss: 0.009236918805993151 | Accuracy: 1.0 Epoch: 1652 | Loss: 0.009227898749168845 | Accuracy: 1.0 Epoch: 1653 | Loss: 0.009218894775574 | Accuracy: 1.0 Epoch: 1654 | Loss: 0.0092099068440897 | Accuracy: 1.0 Epoch: 1655 | Loss: 0.009200934913732991 | Accuracy: 1.0 Epoch: 1656 | Loss: 0.009191978943656478 | Accuracy: 1.0 Epoch: 1657 | Loss: 0.00918303889314802 | Accuracy: 1.0 Epoch: 1658 | Loss: 0.009174114721629328 | Accuracy: 1.0 Epoch: 1659 | Loss: 0.009165206388656772 | Accuracy: 1.0 Epoch: 1660 | Loss: 0.009156313853919426 | Accuracy: 1.0 Epoch: 1661 | Loss: 0.009147437077239312 | Accuracy: 1.0 Epoch: 1662 | Loss: 0.009138576018571116 | Accuracy: 1.0 Epoch: 1663 | Loss: 0.009129730638000908 | Accuracy: 1.0 Epoch: 1664 | Loss: 0.00912090089574599 | Accuracy: 1.0 Epoch: 1665 | Loss: 0.009112086752154594 | Accuracy: 1.0 Epoch: 1666 | Loss: 0.009103288167704914 | Accuracy: 1.0 Epoch: 1667 | Loss: 0.009094505103004843 | Accuracy: 1.0 Epoch: 1668 | Loss: 0.009085737518791397 | Accuracy: 1.0 Epoch: 1669 | Loss: 0.009076985375930213 | Accuracy: 1.0 Epoch: 1670 | Loss: 0.009068248635415263 | Accuracy: 1.0 Epoch: 1671 | Loss: 0.009059527258367433 | Accuracy: 1.0 Epoch: 1672 | Loss: 0.009050821206035373 | Accuracy: 1.0 Epoch: 1673 | Loss: 0.009042130439793974 | Accuracy: 1.0 Epoch: 1674 | Loss: 0.009033454921144261 | Accuracy: 1.0 Epoch: 1675 | Loss: 0.009024794611712817 | Accuracy: 1.0 Epoch: 1676 | Loss: 0.009016149473251293 | Accuracy: 1.0 Epoch: 1677 | Loss: 0.009007519467635613 | Accuracy: 1.0 Epoch: 1678 | Loss: 0.008998904556866274 | Accuracy: 1.0 Epoch: 1679 | Loss: 0.00899030470306695 | Accuracy: 1.0 Epoch: 1680 | Loss: 0.008981719868484546 | Accuracy: 1.0 Epoch: 1681 | Loss: 0.00897315001548846 | Accuracy: 1.0 Epoch: 1682 | Loss: 0.008964595106570225 | Accuracy: 1.0 Epoch: 1683 | Loss: 0.008956055104343186 | Accuracy: 1.0 Epoch: 1684 | Loss: 0.008947529971541471 | Accuracy: 1.0 Epoch: 1685 | Loss: 0.008939019671020013 | Accuracy: 1.0 Epoch: 1686 | Loss: 0.008930524165754012 | Accuracy: 1.0 Epoch: 1687 | Loss: 0.008922043418838201 | Accuracy: 1.0 Epoch: 1688 | Loss: 0.008913577393486744 | Accuracy: 1.0 Epoch: 1689 | Loss: 0.008905126053032345 | Accuracy: 1.0 Epoch: 1690 | Loss: 0.008896689360926123 | Accuracy: 1.0 Epoch: 1691 | Loss: 0.008888267280736974 | Accuracy: 1.0 Epoch: 1692 | Loss: 0.008879859776151196 | Accuracy: 1.0 Epoch: 1693 | Loss: 0.008871466810971736 | Accuracy: 1.0 Epoch: 1694 | Loss: 0.008863088349118428 | Accuracy: 1.0 Epoch: 1695 | Loss: 0.008854724354626716 | Accuracy: 1.0 Epoch: 1696 | Loss: 0.00884637479164766 | Accuracy: 1.0 Epoch: 1697 | Loss: 0.008838039624447307 | Accuracy: 1.0 Epoch: 1698 | Loss: 0.008829718817406528 | Accuracy: 1.0 Epoch: 1699 | Loss: 0.008821412335020108 | Accuracy: 1.0 Epoch: 1700 | Loss: 0.008813120141896724 | Accuracy: 1.0 Epoch: 1701 | Loss: 0.008804842202758262 | Accuracy: 1.0 Epoch: 1702 | Loss: 0.008796578482439477 | Accuracy: 1.0 Epoch: 1703 | Loss: 0.008788328945887347 | Accuracy: 1.0 Epoch: 1704 | Loss: 0.008780093558161072 | Accuracy: 1.0 Epoch: 1705 | Loss: 0.00877187228443094 | Accuracy: 1.0 Epoch: 1706 | Loss: 0.008763665089978782 | Accuracy: 1.0 Epoch: 1707 | Loss: 0.008755471940196833 | Accuracy: 1.0 Epoch: 1708 | Loss: 0.008747292800587437 | Accuracy: 1.0 Epoch: 1709 | Loss: 0.008739127636762888 | Accuracy: 1.0 Epoch: 1710 | Loss: 0.008730976414444844 | Accuracy: 1.0 Epoch: 1711 | Loss: 0.008722839099463708 | Accuracy: 1.0 Epoch: 1712 | Loss: 0.008714715657758476 | Accuracy: 1.0 Epoch: 1713 | Loss: 0.0087066060553764 | Accuracy: 1.0 Epoch: 1714 | Loss: 0.008698510258472066 | Accuracy: 1.0 Epoch: 1715 | Loss: 0.008690428233307543 | Accuracy: 1.0 Epoch: 1716 | Loss: 0.008682359946251694 | Accuracy: 1.0 Epoch: 1717 | Loss: 0.008674305363779677 | Accuracy: 1.0 Epoch: 1718 | Loss: 0.008666264452472733 | Accuracy: 1.0 Epoch: 1719 | Loss: 0.008658237179017668 | Accuracy: 1.0 Epoch: 1720 | Loss: 0.008650223510206598 | Accuracy: 1.0 Epoch: 1721 | Loss: 0.00864222341293621 | Accuracy: 1.0 Epoch: 1722 | Loss: 0.00863423685420758 | Accuracy: 1.0 Epoch: 1723 | Loss: 0.008626263801126133 | Accuracy: 1.0 Epoch: 1724 | Loss: 0.008618304220900139 | Accuracy: 1.0 Epoch: 1725 | Loss: 0.008610358080841877 | Accuracy: 1.0 Epoch: 1726 | Loss: 0.00860242534836583 | Accuracy: 1.0 Epoch: 1727 | Loss: 0.008594505990988814 | Accuracy: 1.0 Epoch: 1728 | Loss: 0.008586599976329944 | Accuracy: 1.0 Epoch: 1729 | Loss: 0.00857870727210995 | Accuracy: 1.0 Epoch: 1730 | Loss: 0.008570827846150403 | Accuracy: 1.0 Epoch: 1731 | Loss: 0.008562961666374026 | Accuracy: 1.0 Epoch: 1732 | Loss: 0.008555108700803922 | Accuracy: 1.0 Epoch: 1733 | Loss: 0.008547268917562915 | Accuracy: 1.0 Epoch: 1734 | Loss: 0.008539442284873886 | Accuracy: 1.0 Epoch: 1735 | Loss: 0.008531628771058798 | Accuracy: 1.0 Epoch: 1736 | Loss: 0.008523828344538607 | Accuracy: 1.0 Epoch: 1737 | Loss: 0.008516040973832698 | Accuracy: 1.0 Epoch: 1738 | Loss: 0.00850826662755856 | Accuracy: 1.0 Epoch: 1739 | Loss: 0.008500505274431601 | Accuracy: 1.0 Epoch: 1740 | Loss: 0.008492756883264587 | Accuracy: 1.0 Epoch: 1741 | Loss: 0.00848502142296708 | Accuracy: 1.0 Epoch: 1742 | Loss: 0.008477298862545734 | Accuracy: 1.0 Epoch: 1743 | Loss: 0.008469589171103135 | Accuracy: 1.0 Epoch: 1744 | Loss: 0.008461892317837925 | Accuracy: 1.0 Epoch: 1745 | Loss: 0.008454208272044243 | Accuracy: 1.0 Epoch: 1746 | Loss: 0.008446537003111296 | Accuracy: 1.0 Epoch: 1747 | Loss: 0.008438878480523652 | Accuracy: 1.0 Epoch: 1748 | Loss: 0.008431232673859762 | Accuracy: 1.0 Epoch: 1749 | Loss: 0.008423599552792427 | Accuracy: 1.0 Epoch: 1750 | Loss: 0.008415979087088224 | Accuracy: 1.0 Epoch: 1751 | Loss: 0.008408371246607064 | Accuracy: 1.0 Epoch: 1752 | Loss: 0.008400776001302058 | Accuracy: 1.0 Epoch: 1753 | Loss: 0.008393193321218743 | Accuracy: 1.0 Epoch: 1754 | Loss: 0.008385623176495478 | Accuracy: 1.0 Epoch: 1755 | Loss: 0.008378065537361978 | Accuracy: 1.0 Epoch: 1756 | Loss: 0.008370520374140088 | Accuracy: 1.0 Epoch: 1757 | Loss: 0.008362987657242962 | Accuracy: 1.0 Epoch: 1758 | Loss: 0.0083554673571744 | Accuracy: 1.0 Epoch: 1759 | Loss: 0.008347959444529042 | Accuracy: 1.0 Epoch: 1760 | Loss: 0.008340463889991824 | Accuracy: 1.0 Epoch: 1761 | Loss: 0.008332980664337589 | Accuracy: 1.0 Epoch: 1762 | Loss: 0.0083255097384307 | Accuracy: 1.0 Epoch: 1763 | Loss: 0.008318051083224998 | Accuracy: 1.0 Epoch: 1764 | Loss: 0.008310604669762906 | Accuracy: 1.0 Epoch: 1765 | Loss: 0.008303170469175888 | Accuracy: 1.0 Epoch: 1766 | Loss: 0.008295748452683306 | Accuracy: 1.0 Epoch: 1767 | Loss: 0.008288338591592599 | Accuracy: 1.0 Epoch: 1768 | Loss: 0.008280940857298948 | Accuracy: 1.0 Epoch: 1769 | Loss: 0.008273555221284529 | Accuracy: 1.0 Epoch: 1770 | Loss: 0.00826618165511875 | Accuracy: 1.0 Epoch: 1771 | Loss: 0.008258820130457409 | Accuracy: 1.0 Epoch: 1772 | Loss: 0.008251470619042842 | Accuracy: 1.0 Epoch: 1773 | Loss: 0.008244133092703127 | Accuracy: 1.0 Epoch: 1774 | Loss: 0.008236807523352188 | Accuracy: 1.0 Epoch: 1775 | Loss: 0.008229493882989452 | Accuracy: 1.0 Epoch: 1776 | Loss: 0.008222192143698976 | Accuracy: 1.0 Epoch: 1777 | Loss: 0.00821490227764977 | Accuracy: 1.0 Epoch: 1778 | Loss: 0.008207624257094967 | Accuracy: 1.0 Epoch: 1779 | Loss: 0.008200358054372425 | Accuracy: 1.0 Epoch: 1780 | Loss: 0.00819310364190305 | Accuracy: 1.0 Epoch: 1781 | Loss: 0.008185860992191657 | Accuracy: 1.0 Epoch: 1782 | Loss: 0.008178630077825945 | Accuracy: 1.0 Epoch: 1783 | Loss: 0.008171410871476863 | Accuracy: 1.0 Epoch: 1784 | Loss: 0.008164203345897365 | Accuracy: 1.0 Epoch: 1785 | Loss: 0.008157007473922936 | Accuracy: 1.0 Epoch: 1786 | Loss: 0.008149823228471055 | Accuracy: 1.0 Epoch: 1787 | Loss: 0.008142650582540701 | Accuracy: 1.0 Epoch: 1788 | Loss: 0.008135489509212139 | Accuracy: 1.0 Epoch: 1789 | Loss: 0.00812833998164673 | Accuracy: 1.0 Epoch: 1790 | Loss: 0.008121201973086667 | Accuracy: 1.0 Epoch: 1791 | Loss: 0.008114075456854265 | Accuracy: 1.0 Epoch: 1792 | Loss: 0.008106960406352365 | Accuracy: 1.0 Epoch: 1793 | Loss: 0.008099856795063271 | Accuracy: 1.0 Epoch: 1794 | Loss: 0.008092764596549071 | Accuracy: 1.0 Epoch: 1795 | Loss: 0.008085683784451046 | Accuracy: 1.0 Epoch: 1796 | Loss: 0.008078614332489489 | Accuracy: 1.0 Epoch: 1797 | Loss: 0.008071556214463281 | Accuracy: 1.0 Epoch: 1798 | Loss: 0.008064509404249666 | Accuracy: 1.0 Epoch: 1799 | Loss: 0.008057473875804137 | Accuracy: 1.0 Epoch: 1800 | Loss: 0.008050449603159728 | Accuracy: 1.0 Epoch: 1801 | Loss: 0.008043436560427289 | Accuracy: 1.0 Epoch: 1802 | Loss: 0.00803643472179477 | Accuracy: 1.0 Epoch: 1803 | Loss: 0.008029444061527027 | Accuracy: 1.0 Epoch: 1804 | Loss: 0.008022464553965773 | Accuracy: 1.0 Epoch: 1805 | Loss: 0.008015496173528997 | Accuracy: 1.0 Epoch: 1806 | Loss: 0.008008538894710721 | Accuracy: 1.0 Epoch: 1807 | Loss: 0.008001592692081078 | Accuracy: 1.0 Epoch: 1808 | Loss: 0.00799465754028552 | Accuracy: 1.0 Epoch: 1809 | Loss: 0.007987733414044733 | Accuracy: 1.0 Epoch: 1810 | Loss: 0.007980820288154885 | Accuracy: 1.0 Epoch: 1811 | Loss: 0.007973918137486314 | Accuracy: 1.0 Epoch: 1812 | Loss: 0.007967026936984064 | Accuracy: 1.0 Epoch: 1813 | Loss: 0.007960146661667597 | Accuracy: 1.0 Epoch: 1814 | Loss: 0.007953277286629909 | Accuracy: 1.0 Epoch: 1815 | Loss: 0.007946418787038024 | Accuracy: 1.0 Epoch: 1816 | Loss: 0.007939571138132087 | Accuracy: 1.0 Epoch: 1817 | Loss: 0.007932734315225669 | Accuracy: 1.0 Epoch: 1818 | Loss: 0.007925908293704913 | Accuracy: 1.0 Epoch: 1819 | Loss: 0.007919093049028735 | Accuracy: 1.0 Epoch: 1820 | Loss: 0.007912288556728285 | Accuracy: 1.0 Epoch: 1821 | Loss: 0.007905494792406993 | Accuracy: 1.0 Epoch: 1822 | Loss: 0.007898711731739849 | Accuracy: 1.0 Epoch: 1823 | Loss: 0.00789193935047367 | Accuracy: 1.0 Epoch: 1824 | Loss: 0.007885177624426259 | Accuracy: 1.0 Epoch: 1825 | Loss: 0.007878426529486872 | Accuracy: 1.0 Epoch: 1826 | Loss: 0.00787168604161519 | Accuracy: 1.0 Epoch: 1827 | Loss: 0.00786495613684161 | Accuracy: 1.0 Epoch: 1828 | Loss: 0.00785823679126685 | Accuracy: 1.0 Epoch: 1829 | Loss: 0.00785152798106143 | Accuracy: 1.0 Epoch: 1830 | Loss: 0.007844829682466038 | Accuracy: 1.0 Epoch: 1831 | Loss: 0.007838141871790546 | Accuracy: 1.0 Epoch: 1832 | Loss: 0.007831464525414228 | Accuracy: 1.0 Epoch: 1833 | Loss: 0.007824797619785417 | Accuracy: 1.0 Epoch: 1834 | Loss: 0.00781814113142118 | Accuracy: 1.0 Epoch: 1835 | Loss: 0.007811495036907122 | Accuracy: 1.0 Epoch: 1836 | Loss: 0.007804859312897254 | Accuracy: 1.0 Epoch: 1837 | Loss: 0.00779823393611355 | Accuracy: 1.0 Epoch: 1838 | Loss: 0.007791618883345728 | Accuracy: 1.0 Epoch: 1839 | Loss: 0.007785014131451087 | Accuracy: 1.0 Epoch: 1840 | Loss: 0.007778419657354396 | Accuracy: 1.0 Epoch: 1841 | Loss: 0.007771835438047317 | Accuracy: 1.0 Epoch: 1842 | Loss: 0.007765261450588657 | Accuracy: 1.0 Epoch: 1843 | Loss: 0.007758697672103316 | Accuracy: 1.0 Epoch: 1844 | Loss: 0.007752144079783174 | Accuracy: 1.0 Epoch: 1845 | Loss: 0.007745600650885713 | Accuracy: 1.0 Epoch: 1846 | Loss: 0.00773906736273465 | Accuracy: 1.0 Epoch: 1847 | Loss: 0.007732544192719227 | Accuracy: 1.0 Epoch: 1848 | Loss: 0.007726031118294176 | Accuracy: 1.0 Epoch: 1849 | Loss: 0.0077195281169794815 | Accuracy: 1.0 Epoch: 1850 | Loss: 0.0077130351663598756 | Accuracy: 1.0 Epoch: 1851 | Loss: 0.00770655224408504 | Accuracy: 1.0 Epoch: 1852 | Loss: 0.00770007932786905 | Accuracy: 1.0 Epoch: 1853 | Loss: 0.007693616395490408 | Accuracy: 1.0 Epoch: 1854 | Loss: 0.0076871634247916 | Accuracy: 1.0 Epoch: 1855 | Loss: 0.007680720393678765 | Accuracy: 1.0 Epoch: 1856 | Loss: 0.00767428728012195 | Accuracy: 1.0 Epoch: 1857 | Loss: 0.007667864062154273 | Accuracy: 1.0 Epoch: 1858 | Loss: 0.0076614507178723226 | Accuracy: 1.0 Epoch: 1859 | Loss: 0.007655047225435408 | Accuracy: 1.0 Epoch: 1860 | Loss: 0.007648653563065558 | Accuracy: 1.0 Epoch: 1861 | Loss: 0.0076422697090473045 | Accuracy: 1.0 Epoch: 1862 | Loss: 0.007635895641727548 | Accuracy: 1.0 Epoch: 1863 | Loss: 0.007629531339515194 | Accuracy: 1.0 Epoch: 1864 | Loss: 0.007623176780881022 | Accuracy: 1.0 Epoch: 1865 | Loss: 0.007616831944357187 | Accuracy: 1.0 Epoch: 1866 | Loss: 0.0076104968085375785 | Accuracy: 1.0 Epoch: 1867 | Loss: 0.007604171352076997 | Accuracy: 1.0 Epoch: 1868 | Loss: 0.007597855553691426 | Accuracy: 1.0 Epoch: 1869 | Loss: 0.007591549392157405 | Accuracy: 1.0 Epoch: 1870 | Loss: 0.00758525284631233 | Accuracy: 1.0 Epoch: 1871 | Loss: 0.007578965895053599 | Accuracy: 1.0 Epoch: 1872 | Loss: 0.007572688517338945 | Accuracy: 1.0 Epoch: 1873 | Loss: 0.007566420692185832 | Accuracy: 1.0 Epoch: 1874 | Loss: 0.007560162398671507 | Accuracy: 1.0 Epoch: 1875 | Loss: 0.007553913615932896 | Accuracy: 1.0 Epoch: 1876 | Loss: 0.007547674323165937 | Accuracy: 1.0 Epoch: 1877 | Loss: 0.007541444499625834 | Accuracy: 1.0 Epoch: 1878 | Loss: 0.007535224124626394 | Accuracy: 1.0 Epoch: 1879 | Loss: 0.0075290131775406915 | Accuracy: 1.0 Epoch: 1880 | Loss: 0.0075228116377995214 | Accuracy: 1.0 Epoch: 1881 | Loss: 0.007516619484892396 | Accuracy: 1.0 Epoch: 1882 | Loss: 0.00751043669836691 | Accuracy: 1.0 Epoch: 1883 | Loss: 0.007504263257828247 | Accuracy: 1.0 Epoch: 1884 | Loss: 0.00749809914293951 | Accuracy: 1.0 Epoch: 1885 | Loss: 0.007491944333421114 | Accuracy: 1.0 Epoch: 1886 | Loss: 0.007485798809050707 | Accuracy: 1.0 Epoch: 1887 | Loss: 0.007479662549663279 | Accuracy: 1.0 Epoch: 1888 | Loss: 0.007473535535150143 | Accuracy: 1.0 Epoch: 1889 | Loss: 0.007467417745459987 | Accuracy: 1.0 Epoch: 1890 | Loss: 0.0074613091605973784 | Accuracy: 1.0 Epoch: 1891 | Loss: 0.007455209760623353 | Accuracy: 1.0 Epoch: 1892 | Loss: 0.007449119525655189 | Accuracy: 1.0 Epoch: 1893 | Loss: 0.007443038435865773 | Accuracy: 1.0 Epoch: 1894 | Loss: 0.007436966471484048 | Accuracy: 1.0 Epoch: 1895 | Loss: 0.007430903612794042 | Accuracy: 1.0 Epoch: 1896 | Loss: 0.0074248498401355105 | Accuracy: 1.0 Epoch: 1897 | Loss: 0.007418805133902964 | Accuracy: 1.0 Epoch: 1898 | Loss: 0.007412769474546145 | Accuracy: 1.0 Epoch: 1899 | Loss: 0.007406742842569444 | Accuracy: 1.0 Epoch: 1900 | Loss: 0.007400725218531656 | Accuracy: 1.0 Epoch: 1901 | Loss: 0.007394716583045978 | Accuracy: 1.0 Epoch: 1902 | Loss: 0.007388716916780236 | Accuracy: 1.0 Epoch: 1903 | Loss: 0.00738272620045561 | Accuracy: 1.0 Epoch: 1904 | Loss: 0.0073767444148475775 | Accuracy: 1.0 Epoch: 1905 | Loss: 0.007370771540785002 | Accuracy: 1.0 Epoch: 1906 | Loss: 0.007364807559150217 | Accuracy: 1.0 Epoch: 1907 | Loss: 0.007358852450878918 | Accuracy: 1.0 Epoch: 1908 | Loss: 0.0073529061969597196 | Accuracy: 1.0 Epoch: 1909 | Loss: 0.007346968778434462 | Accuracy: 1.0 Epoch: 1910 | Loss: 0.007341040176397213 | Accuracy: 1.0 Epoch: 1911 | Loss: 0.007335120371995026 | Accuracy: 1.0 Epoch: 1912 | Loss: 0.007329209346427125 | Accuracy: 1.0 Epoch: 1913 | Loss: 0.007323307080944865 | Accuracy: 1.0 Epoch: 1914 | Loss: 0.007317413556851719 | Accuracy: 1.0 Epoch: 1915 | Loss: 0.007311528755502934 | Accuracy: 1.0 Epoch: 1916 | Loss: 0.0073056526583054945 | Accuracy: 1.0 Epoch: 1917 | Loss: 0.007299785246717766 | Accuracy: 1.0 Epoch: 1918 | Loss: 0.007293926502249332 | Accuracy: 1.0 Epoch: 1919 | Loss: 0.007288076406461163 | Accuracy: 1.0 Epoch: 1920 | Loss: 0.007282234940964922 | Accuracy: 1.0 Epoch: 1921 | Loss: 0.007276402087423273 | Accuracy: 1.0 Epoch: 1922 | Loss: 0.007270577827549356 | Accuracy: 1.0 Epoch: 1923 | Loss: 0.007264762143106842 | Accuracy: 1.0 Epoch: 1924 | Loss: 0.0072589550159094084 | Accuracy: 1.0 Epoch: 1925 | Loss: 0.00725315642782119 | Accuracy: 1.0 Epoch: 1926 | Loss: 0.007247366360756048 | Accuracy: 1.0 Epoch: 1927 | Loss: 0.007241584796677779 | Accuracy: 1.0 Epoch: 1928 | Loss: 0.007235811717599273 | Accuracy: 1.0 Epoch: 1929 | Loss: 0.007230047105583743 | Accuracy: 1.0 Epoch: 1930 | Loss: 0.007224290942742839 | Accuracy: 1.0 Epoch: 1931 | Loss: 0.007218543211237561 | Accuracy: 1.0 Epoch: 1932 | Loss: 0.007212803893278019 | Accuracy: 1.0 Epoch: 1933 | Loss: 0.007207072971122951 | Accuracy: 1.0 Epoch: 1934 | Loss: 0.007201350427079491 | Accuracy: 1.0 Epoch: 1935 | Loss: 0.007195636243503597 | Accuracy: 1.0 Epoch: 1936 | Loss: 0.007189930402799316 | Accuracy: 1.0 Epoch: 1937 | Loss: 0.007184232887418673 | Accuracy: 1.0 Epoch: 1938 | Loss: 0.007178543679861916 | Accuracy: 1.0 Epoch: 1939 | Loss: 0.007172862762676859 | Accuracy: 1.0 Epoch: 1940 | Loss: 0.007167190118459045 | Accuracy: 1.0 Epoch: 1941 | Loss: 0.0071615257298515 | Accuracy: 1.0 Epoch: 1942 | Loss: 0.007155869579544597 | Accuracy: 1.0 Epoch: 1943 | Loss: 0.007150221650275639 | Accuracy: 1.0 Epoch: 1944 | Loss: 0.007144581924829141 | Accuracy: 1.0 Epoch: 1945 | Loss: 0.0071389503860363815 | Accuracy: 1.0 Epoch: 1946 | Loss: 0.0071333270167754405 | Accuracy: 1.0 Epoch: 1947 | Loss: 0.007127711799970778 | Accuracy: 1.0 Epoch: 1948 | Loss: 0.007122104718593185 | Accuracy: 1.0 Epoch: 1949 | Loss: 0.007116505755660057 | Accuracy: 1.0 Epoch: 1950 | Loss: 0.007110914894234096 | Accuracy: 1.0 Epoch: 1951 | Loss: 0.007105332117424697 | Accuracy: 1.0 Epoch: 1952 | Loss: 0.007099757408386734 | Accuracy: 1.0 Epoch: 1953 | Loss: 0.007094190750320271 | Accuracy: 1.0 Epoch: 1954 | Loss: 0.007088632126471579 | Accuracy: 1.0 Epoch: 1955 | Loss: 0.007083081520131766 | Accuracy: 1.0 Epoch: 1956 | Loss: 0.007077538914637172 | Accuracy: 1.0 Epoch: 1957 | Loss: 0.007072004293369008 | Accuracy: 1.0 Epoch: 1958 | Loss: 0.007066477639753662 | Accuracy: 1.0 Epoch: 1959 | Loss: 0.007060958937261818 | Accuracy: 1.0 Epoch: 1960 | Loss: 0.007055448169409198 | Accuracy: 1.0 Epoch: 1961 | Loss: 0.007049945319755739 | Accuracy: 1.0 Epoch: 1962 | Loss: 0.007044450371905284 | Accuracy: 1.0 Epoch: 1963 | Loss: 0.0070389633095061695 | Accuracy: 1.0 Epoch: 1964 | Loss: 0.007033484116250833 | Accuracy: 1.0 Epoch: 1965 | Loss: 0.0070280127758751585 | Accuracy: 1.0 Epoch: 1966 | Loss: 0.007022549272158911 | Accuracy: 1.0 Epoch: 1967 | Loss: 0.007017093588925441 | Accuracy: 1.0 Epoch: 1968 | Loss: 0.007011645710041429 | Accuracy: 1.0 Epoch: 1969 | Loss: 0.007006205619416755 | Accuracy: 1.0 Epoch: 1970 | Loss: 0.007000773301004495 | Accuracy: 1.0 Epoch: 1971 | Loss: 0.006995348738800537 | Accuracy: 1.0 Epoch: 1972 | Loss: 0.006989931916843859 | Accuracy: 1.0 Epoch: 1973 | Loss: 0.006984522819216112 | Accuracy: 1.0 Epoch: 1974 | Loss: 0.0069791214300411525 | Accuracy: 1.0 Epoch: 1975 | Loss: 0.00697372773348546 | Accuracy: 1.0 Epoch: 1976 | Loss: 0.006968341713757885 | Accuracy: 1.0 Epoch: 1977 | Loss: 0.006962963355109267 | Accuracy: 1.0 Epoch: 1978 | Loss: 0.006957592641832516 | Accuracy: 1.0 Epoch: 1979 | Loss: 0.006952229558262282 | Accuracy: 1.0 Epoch: 1980 | Loss: 0.006946874088775094 | Accuracy: 1.0 Epoch: 1981 | Loss: 0.006941526217788971 | Accuracy: 1.0 Epoch: 1982 | Loss: 0.006936185929763266 | Accuracy: 1.0 Epoch: 1983 | Loss: 0.006930853209198876 | Accuracy: 1.0 Epoch: 1984 | Loss: 0.006925528040637809 | Accuracy: 1.0 Epoch: 1985 | Loss: 0.006920210408662989 | Accuracy: 1.0 Epoch: 1986 | Loss: 0.006914900297898309 | Accuracy: 1.0 Epoch: 1987 | Loss: 0.006909597693008332 | Accuracy: 1.0 Epoch: 1988 | Loss: 0.006904302578698734 | Accuracy: 1.0 Epoch: 1989 | Loss: 0.006899014939715084 | Accuracy: 1.0 Epoch: 1990 | Loss: 0.006893734760843706 | Accuracy: 1.0 Epoch: 1991 | Loss: 0.006888462026910876 | Accuracy: 1.0 Epoch: 1992 | Loss: 0.006883196722783433 | Accuracy: 1.0 Epoch: 1993 | Loss: 0.006877938833367784 | Accuracy: 1.0 Epoch: 1994 | Loss: 0.006872688343610397 | Accuracy: 1.0 Epoch: 1995 | Loss: 0.006867445238497425 | Accuracy: 1.0 Epoch: 1996 | Loss: 0.006862209503054615 | Accuracy: 1.0 Epoch: 1997 | Loss: 0.006856981122347146 | Accuracy: 1.0 Epoch: 1998 | Loss: 0.006851760081479632 | Accuracy: 1.0 Epoch: 1999 | Loss: 0.006846546365595982 | Accuracy: 1.0 Epoch: 2000 | Loss: 0.006841339959878705 | Accuracy: 1.0
plot_colored_graph(model, X, y)
<ipython-input-13-ff87a8808486>:9: MatplotlibDeprecationWarning: shading='flat' when X and Y have the same dimensions as C is deprecated since 3.3. Either specify the corners of the quadrilaterals with X and Y, or pass shading='auto', 'nearest' or 'gouraud', or set rcParams['pcolor.shading']. This will become an error two minor releases later. plt.pcolormesh(xx, yy, Z, cmap=cmap_light)